diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..41478957aca7a04b7321022e7d1f73de5badd995 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{{ visible_text(m.content) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson(ensure_ascii=False) if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '\n' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f1c84cb5930ca1a0499e77c4b690e478323aa856 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "pad_token_id": 151329, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "partial_rotary_factor": 0.5, + "initializer_range": 0.02, + "intermediate_size": 10944, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1408, + "norm_topk_prob": true, + "num_attention_heads": 96, + "n_group": 1, + "topk_group": 1, + "n_routed_experts": 128, + "n_shared_experts": 1, + "routed_scaling_factor": 1.0, + "num_experts_per_tok": 8, + "first_k_dense_replace": 1, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "num_nextn_predict_layers": 1, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.0", + "use_cache": true, + "use_qk_norm": false, + "vocab_size": 151552 +} \ No newline at end of file diff --git a/model-00001-of-00047.safetensors b/model-00001-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53793efe7633f12721d322020e554754840623c2 --- /dev/null +++ b/model-00001-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf40ee4cfb4064cc3bdebddc5eb84808815b3908ad40611e1825e7f8d8bd56f2 +size 2970138176 diff --git a/model-00002-of-00047.safetensors b/model-00002-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da39b0302a31dc11793ea386f24f80b04cad8f21 --- /dev/null +++ b/model-00002-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df5534eec7264f9a87204715bb81d5bfd55849e1fd0fa0af118e2e0ca67d01f +size 4683035216 diff --git a/model-00003-of-00047.safetensors b/model-00003-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe66d2c73ea1f427fc6ee2fb075b789c919ce9d7 --- /dev/null +++ b/model-00003-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e621684a989e629eb35c884da0c8961c245b157758bb950c8f36a789689b3603 +size 4683035216 diff --git a/model-00004-of-00047.safetensors b/model-00004-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec2644fbaacf7119f1e641ad926de0f5796fd53e --- /dev/null +++ b/model-00004-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d2e2d1028484c15add591acf12e393a492f1adcfae16a09413fdb0d14cd3c7d +size 4683035216 diff --git a/model-00005-of-00047.safetensors b/model-00005-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af22f29948d10b8545411c23ba08e7e9aac733ed --- /dev/null +++ b/model-00005-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701af98fe4f9b04c0e2b81a892bae644e78c49c967ef882cea53a8e8c7bc73d8 +size 4683035216 diff --git a/model-00006-of-00047.safetensors b/model-00006-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6505878fefa29684d56740b5e4130cc29ec79655 --- /dev/null +++ b/model-00006-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d64fea65939fcd4b92e6ab0b7a6b6b7870957d7c6cd052fad0b32a38dd1d26 +size 4683035216 diff --git a/model-00007-of-00047.safetensors b/model-00007-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f87db5ac954766b143fe4f326b0c810d92b41c43 --- /dev/null +++ b/model-00007-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba688b9f983776c155d21754f429af741963c0e9a54c50361eb323afe603b4d +size 4683035216 diff --git a/model-00008-of-00047.safetensors b/model-00008-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f04ef8c00bff3f7ac228e62bfb8aee9503227e50 --- /dev/null +++ b/model-00008-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd56cf39c66f2ac667237ad3e4f0fc93d12d63f6a15c5af91c25ac2d59229aaf +size 4683035216 diff --git a/model-00009-of-00047.safetensors b/model-00009-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d229c3ef64f6a4a95740e43b6e58feaf8705b450 --- /dev/null +++ b/model-00009-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d7f37b7723baeb39f9127c58c18808711904554fc762fb00ab4ee5188eefe6 +size 4683035216 diff --git a/model-00010-of-00047.safetensors b/model-00010-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46861a3b2211369b1174c568ab937024b7a069b1 --- /dev/null +++ b/model-00010-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e9e60dd8c68a3c4305baf4430a5dbb602ab6a07175c62972c94533ba34f4686 +size 4683035216 diff --git a/model-00011-of-00047.safetensors b/model-00011-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1cde59113d9e0b68ad09e6f5876c761c7b5e50c --- /dev/null +++ b/model-00011-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96dec0a131067829287e5531022c1614250de3e3699629bccbcbab727b6c3316 +size 4683035616 diff --git a/model-00012-of-00047.safetensors b/model-00012-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..02a3fbad83d5a48432044392e5d7912685dd5c5d --- /dev/null +++ b/model-00012-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c09b419e56149d209626e3c2da88c868edb2f41821e4c32b796a52dea292135 +size 4683035616 diff --git a/model-00013-of-00047.safetensors b/model-00013-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..300f03d6ed8c65ecec765d0a94f2e2904fd3d350 --- /dev/null +++ b/model-00013-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda1bd4f1f303327954665261198f6c9e0f89758b1e3469d01ace18c171bd46c +size 4683035616 diff --git a/model-00014-of-00047.safetensors b/model-00014-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12b23e4054fa356bcc1facea23239eeba196e8a4 --- /dev/null +++ b/model-00014-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1243e0d0c443b50704b6b4d0d1642b24d6aca2f20db81bbd8fa3aaf9afdfd39 +size 4683035616 diff --git a/model-00015-of-00047.safetensors b/model-00015-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d7dc5ddc9a85d5b21da9b976e402dbb8bda8ee3 --- /dev/null +++ b/model-00015-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e46a491c1631a6f61b5cb0e490b952d877242152e9fca4e1cd265db2a6cdf2 +size 4683035616 diff --git a/model-00016-of-00047.safetensors b/model-00016-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0255b73aa79ceff27dffbf4261e8c5f6a697a85d --- /dev/null +++ b/model-00016-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdabf61b71c200bf0b3b443b89f20e09129ef45a4eb53680724a74f710ac1e7b +size 4683035616 diff --git a/model-00017-of-00047.safetensors b/model-00017-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f4608af36ae7dd4d1aaaf2a8b1a1319debc5cf42 --- /dev/null +++ b/model-00017-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29ae88bbbb1008081488a53d869159df43513f3250efcc14478be2c8574c8b2 +size 4683035616 diff --git a/model-00018-of-00047.safetensors b/model-00018-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ebd380cfcc9172c1d5df639948bf3c91135b5d6 --- /dev/null +++ b/model-00018-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85906cfba9319dd4f5ea45190a4115249e0bc092f9a5364ac37decb7261fba8 +size 4683035616 diff --git a/model-00019-of-00047.safetensors b/model-00019-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..635e8efc0eb8cef75fc837a712a797cbdba8e83d --- /dev/null +++ b/model-00019-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce53f6795024b6dd01939a3781ef2798aa6706cdc2791663bdb5a2a2123e9533 +size 4683035616 diff --git a/model-00020-of-00047.safetensors b/model-00020-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7764e4b85e86d08c3ca7818d8a3a7e0c7fcb2e0 --- /dev/null +++ b/model-00020-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44fb25c231b3064b1c42617f0b0ba6febd78dc673db72516c003766f8595d3d8 +size 4683035616 diff --git a/model-00021-of-00047.safetensors b/model-00021-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b95d99f6ffbb00a9da21ac5f519dc0503a38b90e --- /dev/null +++ b/model-00021-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e4dc2f2ca6f192a44a842845591b1cd4ec7f104fbebed8f95c4ebafeddedd4b +size 4683035616 diff --git a/model-00022-of-00047.safetensors b/model-00022-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3375d5999fc1c46f98a3c726920628d6b96475f0 --- /dev/null +++ b/model-00022-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97ac4eeed0c452d672ea9294940261a5302a8e9fdcedc5bd6afd95a481134e8 +size 4683035616 diff --git a/model-00023-of-00047.safetensors b/model-00023-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36cd45aa3a71058651a2944863a13f0f9469939e --- /dev/null +++ b/model-00023-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eac740c84803cf4aa648589ef653fbabb061202cad838e58400aa6d3a9d1a57 +size 4683035616 diff --git a/model-00024-of-00047.safetensors b/model-00024-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2d38c2753f20c924fa67dd620cc526bfaf3e781 --- /dev/null +++ b/model-00024-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f5ea9831d1d791a09b67ae1907b9d04a4aec7891e3a06b2061faf46c111fe3 +size 4683035616 diff --git a/model-00025-of-00047.safetensors b/model-00025-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e97700977b95f3d76154ae5d58d9c792c6e5e403 --- /dev/null +++ b/model-00025-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c5f160a451b604603bca502c98d53b2de85526afbd86340d0376ea4f20b2c7 +size 4683035616 diff --git a/model-00026-of-00047.safetensors b/model-00026-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c6ce6e6b8c0378a2ebb275aa53fd9b1acf48501 --- /dev/null +++ b/model-00026-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e024ae4836ab68412f7aba85708ca84c6d7d6494792d15711505278b2431af9 +size 4683035616 diff --git a/model-00027-of-00047.safetensors b/model-00027-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17861e508e7de14f6bbf9fc0bc31947d97ced0ea --- /dev/null +++ b/model-00027-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea2d70cefbbae4c9a1b4fb9fea921125415df2cd90bd959726e1acd5f60e1ccc +size 4683035616 diff --git a/model-00028-of-00047.safetensors b/model-00028-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac81deff6aed6f06c07e7348dcf523a0821c659b --- /dev/null +++ b/model-00028-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ccac189bb1536d2f3af4670f8009a4344c1141b4002d03b4a0236d63048a787 +size 4683035616 diff --git a/model-00029-of-00047.safetensors b/model-00029-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67e1a1c7987d402925bb18a286eac6d35954b3a5 --- /dev/null +++ b/model-00029-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b326f31362528b83655e0d13c30e4484560976a0c2a56d349213db7be37f1a79 +size 4683035616 diff --git a/model-00030-of-00047.safetensors b/model-00030-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..754992c79a5876a8a6f29cf62e7f4276a171c116 --- /dev/null +++ b/model-00030-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b8c1d982a8613050cbbb4bccee9b3b9fed114b5c4bdc3caacd2406bffbadd12 +size 4683035616 diff --git a/model-00031-of-00047.safetensors b/model-00031-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63542478289bf96c7555e0c2f37f4f19adb62571 --- /dev/null +++ b/model-00031-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:665ec1bd1bed6820aa2d09ba82d583a9ef304f64b9b9cdac30caaac8792023c5 +size 4683035616 diff --git a/model-00032-of-00047.safetensors b/model-00032-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8a69c89f58ad15fcb2f396deebdda0f3683629c --- /dev/null +++ b/model-00032-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc765c6d5d2265a4f5cab5ea78d8770d4b666c8df78dd240a4c0ee3f54ee8f6 +size 4683035616 diff --git a/model-00033-of-00047.safetensors b/model-00033-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..113e2167345c865dc1c957e653c98501619a9737 --- /dev/null +++ b/model-00033-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9044129e80741207d2156f93f0f6e736455c404772d371abe3d2895df72bf2c +size 4683035616 diff --git a/model-00034-of-00047.safetensors b/model-00034-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3159ffd39f194f9b71b4526063f1699d8fb71a52 --- /dev/null +++ b/model-00034-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2588930866ddef08c7e310df044deb0e2ae0ae4ada5a80319fc87b60e9e33914 +size 4683035616 diff --git a/model-00035-of-00047.safetensors b/model-00035-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53b52f951b25c1de93e6c191469eba4635696faa --- /dev/null +++ b/model-00035-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a67bf4c828c51601ae5a54ecbc030e6e4eb89ff5e29361797b764f3778008b +size 4683035616 diff --git a/model-00036-of-00047.safetensors b/model-00036-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2418020105716d724db69a78abaa034ce871c517 --- /dev/null +++ b/model-00036-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:398234ceda03cf27e800c659df7086c3377c0a86df621c0773cd11d800204a28 +size 4683035616 diff --git a/model-00037-of-00047.safetensors b/model-00037-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2afb4501fc9640213fa3f172fe171934cd487307 --- /dev/null +++ b/model-00037-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb25fbfe67387390e13c58a5e712b5f7f83c3922dda426b26c5c9be1fe4f01c +size 4683035616 diff --git a/model-00038-of-00047.safetensors b/model-00038-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cfcbd802dad3b71302ada086786ed3e203ca6ecf --- /dev/null +++ b/model-00038-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da9eb496ce1fee40dd02fdc8491515270c839730b7562fc8c593a45560e97efe +size 4683035616 diff --git a/model-00039-of-00047.safetensors b/model-00039-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb0bb2425d2d2848fc2c9fc8706be236f8267a5a --- /dev/null +++ b/model-00039-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c51db4b6e32fcd495c37ea7e6874ad71a176bd8d593500664dbe57522181e21b +size 4683035616 diff --git a/model-00040-of-00047.safetensors b/model-00040-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4932fdb6eba23b9c857ae3235718c9c324dc0e1d --- /dev/null +++ b/model-00040-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab61c5a5dd731ec385f0fe8b9a00c14ab21aaf1de7f0ef3097e6b4920bde347 +size 4683035616 diff --git a/model-00041-of-00047.safetensors b/model-00041-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1f391cab11d4a4869c220822a1bebc7579b21d4 --- /dev/null +++ b/model-00041-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ebee4e911c738b3cfdd77540553413267d7ab646e34e223dec5daf7334324ef +size 4683035616 diff --git a/model-00042-of-00047.safetensors b/model-00042-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57706fc9d0eab4f287831de0ed6020886a72d6f1 --- /dev/null +++ b/model-00042-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccab153b1b90f1f510b45ac3c8524772d67c21e349a4303197a794b85b5d248 +size 4683035616 diff --git a/model-00043-of-00047.safetensors b/model-00043-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10073b59a59009c756a4c4773dc2d11fd808fb05 --- /dev/null +++ b/model-00043-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a958b0b38d2a7c9e6a89b3123aa341eadf6ed6f730c0395b75d08f2bedb07b4 +size 4683035616 diff --git a/model-00045-of-00047.safetensors b/model-00045-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7e4b37713a0c19911e9cacbbe7607372ab5aa13 --- /dev/null +++ b/model-00045-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13a9eef0444c4d25401c8e7008cc693a0a8a3eb2ae2a15620a76ef7f2a2a235a +size 4683035616 diff --git a/model-00047-of-00047.safetensors b/model-00047-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2fd3ac3c293097d43dcf775e40dcacee69d24347 --- /dev/null +++ b/model-00047-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd077dc9b9e37b276df529f84227c59c3477f03c53b2538f2bccb2c9806e7c96 +size 4750169496 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ce8f180497f35d69aaafa863a050e5094790e8bb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,18336 @@ +{ + "metadata": { + "total_size": 110468824832 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00047.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00047.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.46.embed_tokens.weight": "model-00001-of-00047.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00047.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00047.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00047.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00047.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00047.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00047.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00047.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00047.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00047.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00047.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00047.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00047.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00047.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00047.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00047.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00047.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00047.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00047.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00047.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00047.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00047.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00047.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00047.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00047.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00047.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00047.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00011-of-00047.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00011-of-00047.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00011-of-00047.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00012-of-00047.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00012-of-00047.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00012-of-00047.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00013-of-00047.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00013-of-00047.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00013-of-00047.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00014-of-00047.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00014-of-00047.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00014-of-00047.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00047.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00015-of-00047.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00015-of-00047.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00015-of-00047.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00016-of-00047.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00016-of-00047.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00016-of-00047.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00017-of-00047.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00017-of-00047.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00017-of-00047.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00018-of-00047.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00018-of-00047.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00018-of-00047.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00019-of-00047.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00019-of-00047.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00019-of-00047.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00047.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00020-of-00047.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00020-of-00047.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00020-of-00047.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00021-of-00047.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00021-of-00047.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00021-of-00047.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00022-of-00047.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00022-of-00047.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00022-of-00047.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00023-of-00047.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00023-of-00047.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00023-of-00047.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00024-of-00047.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00024-of-00047.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00024-of-00047.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00047.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00025-of-00047.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00025-of-00047.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00025-of-00047.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00026-of-00047.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00026-of-00047.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00026-of-00047.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00027-of-00047.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00027-of-00047.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00027-of-00047.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00028-of-00047.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00028-of-00047.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00028-of-00047.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00029-of-00047.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00029-of-00047.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00029-of-00047.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00047.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00030-of-00047.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00030-of-00047.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00030-of-00047.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00031-of-00047.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00031-of-00047.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00031-of-00047.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00032-of-00047.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00032-of-00047.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00032-of-00047.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.32.input_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00033-of-00047.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00033-of-00047.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00033-of-00047.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.33.input_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00034-of-00047.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00034-of-00047.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00034-of-00047.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.34.input_layernorm.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00035-of-00047.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00035-of-00047.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00035-of-00047.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00035-of-00047.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.35.input_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00036-of-00047.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00036-of-00047.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00036-of-00047.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.36.input_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00037-of-00047.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00037-of-00047.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00037-of-00047.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.37.input_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00038-of-00047.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00038-of-00047.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00038-of-00047.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.38.input_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00039-of-00047.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00039-of-00047.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00039-of-00047.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.39.input_layernorm.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00040-of-00047.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00040-of-00047.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00040-of-00047.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00040-of-00047.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.40.input_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00041-of-00047.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00041-of-00047.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00041-of-00047.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.41.input_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00042-of-00047.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00042-of-00047.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00042-of-00047.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.42.input_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00043-of-00047.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00043-of-00047.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00043-of-00047.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.43.input_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00044-of-00047.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00044-of-00047.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00044-of-00047.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.44.input_layernorm.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00047.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00045-of-00047.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00045-of-00047.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00045-of-00047.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00045-of-00047.safetensors", + "lm_head.weight": "model-00046-of-00047.safetensors", + "model.layers.45.input_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00046-of-00047.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00046-of-00047.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00046-of-00047.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.46.shared_head.head.weight": "model-00046-of-00047.safetensors", + "model.norm.weight": "model-00046-of-00047.safetensors", + "model.layers.46.eh_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.enorm.weight": "model-00047-of-00047.safetensors", + "model.layers.46.hnorm.weight": "model-00047-of-00047.safetensors", + "model.layers.46.input_layernorm.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.100.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.100.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.100.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.101.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.101.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.101.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.102.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.102.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.102.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.103.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.103.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.103.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.104.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.104.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.104.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.105.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.105.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.105.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.106.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.106.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.106.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.107.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.107.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.107.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.108.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.108.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.108.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.109.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.109.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.109.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.110.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.110.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.110.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.111.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.111.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.111.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.112.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.112.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.112.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.113.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.113.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.113.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.114.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.114.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.114.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.115.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.115.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.115.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.116.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.116.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.116.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.117.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.117.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.117.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.118.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.118.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.118.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.119.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.119.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.119.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.120.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.120.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.120.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.121.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.121.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.121.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.122.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.122.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.122.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.123.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.123.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.123.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.124.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.124.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.124.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.125.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.125.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.125.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.126.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.126.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.126.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.127.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.127.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.127.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.64.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.64.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.64.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.65.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.65.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.65.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.66.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.66.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.66.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.67.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.67.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.67.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.68.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.68.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.68.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.69.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.69.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.69.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.70.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.70.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.70.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.71.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.71.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.71.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.72.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.72.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.72.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.73.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.73.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.73.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.74.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.74.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.74.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.75.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.75.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.75.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.76.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.76.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.76.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.77.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.77.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.77.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.78.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.78.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.78.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.79.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.79.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.79.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.80.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.80.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.80.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.81.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.81.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.81.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.82.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.82.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.82.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.83.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.83.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.83.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.84.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.84.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.84.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.85.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.85.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.85.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.86.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.86.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.86.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.87.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.87.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.87.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.88.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.88.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.88.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.89.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.89.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.89.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.90.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.90.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.90.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.91.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.91.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.91.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.92.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.92.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.92.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.93.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.93.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.93.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.94.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.94.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.94.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.95.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.95.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.95.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.96.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.96.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.96.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.97.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.97.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.97.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.98.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.98.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.98.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.99.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.99.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.experts.99.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.gate.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00047-of-00047.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00047-of-00047.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00047-of-00047.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00047-of-00047.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00047-of-00047.safetensors", + "model.layers.46.shared_head.norm.weight": "model-00047-of-00047.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..43a71efad1ab3f7e4d66d1e48e7cc44f68f21f3a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd +size 19970699 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..053f12c9b03d5acbcc921042ea0c87a6baa5d3f7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,325 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizer" +}