Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "cognitivecomputations/WestLake-7B-v2-laser",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,43 @@
+base_model: cognitivecomputations/WestLake-7B-v2-laser
+gate_mode: approach
+dtype: bfloat16
+experts:
+  - source_model: mlabonne/Daredevil-7B
+    positive_prompts:
+      - "Answer this question from the ARC (Argument Reasoning Comprehension)."
+      - "Use common sense and logical reasoning skills."
+    negative_prompts:
+      - "nonsense"
+      - "irrational"
+      - "math"
+      - "code"
+  - source_model: cognitivecomputations/WestLake-7B-v2-laser
+    positive_prompts:
+      - "Answer this question from the Winogrande test."
+      - "Use advanced knowledge of culture and humanity"
+    negative_prompts:
+      - "ignorance"
+      - "uninformed"
+      - "creativity"
+  - source_model: mlabonne/Daredevil-7B
+    positive_prompts:
+      - "Calculate the answer to this math problem"
+      - "My mathematical capabilities are strong, allowing me to handle complex mathematical queries"
+      - "solve for"
+    negative_prompts:
+      - "incorrect"
+      - "inaccurate"
+      - "creativity"
+  - source_model: Treza12/Biomistral-Class1111-Full
+    positive_prompts:
+      - "Provide a detailed explanation based on medical literature."
+      - "Apply clinical reasoning to answer this healthcare question."
+      - "Use biomedical knowledge to solve this problem."
+      - "Interpret these clinical findings in the context of patient care."
+      - "Leverage your understanding of healthcare systems to advise on policy."
+    negative_prompts:
+      - "vague"
+      - "non-scientific"
+      - "unrelated to healthcare"
+      - "simplistic understanding"
+      - "ignore clinical guidelines"

model-00001-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01404c5f44c008c735f87bff552b140f17d3125461eb54986323a6ac38083473
+size 991970880

model-00002-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c34e12b084fb95e2979f1c42b62a9e99f0f7c56ba83cce0562ac83b5f33060b
+size 905987800

model-00003-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f477f62aa3c83f9830f3e01f741c5b990d6e79989cf480ada33fe4295652405e
+size 998253976

model-00004-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119c754f989f30be4793d7e44d504190cd44c40346e980ae61a0aeff053d18ac
+size 905979504

model-00005-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6fc7fbc66b9b0134daa3fe3bf29cfcbabe3ae29aea83043e63ef61a2d52613
+size 905987800

model-00006-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe21537508db1586d8eac9d8443680299c34474cd668ce2bfc93bf3e4cc55148
+size 905987800

model-00007-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34f3594a31af77f250184b66590d8cfdaa07776a194591002b18c2c7a80cc8a
+size 939525296

model-00008-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3d89946ba92a2f04a332a5e877c26b01891ab4891601e59627262343fa6763
+size 905987800

model-00009-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02bb048d7ba27614ac14b05948bc4e45b0947554f505cd391e317601ee36272
+size 905987800

model-00010-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccfcd909e4c04e5ac0e1925ad97d12bba4e3d170c9ad436b218213d74e4960f
+size 939525296

model-00011-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f191fcf7627fead52c1a10082226f85a4cd8f7a90412d8124f4abe307b52406
+size 905987800

model-00012-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdb53ef47e372f1b233ee0eda34758a6de7289afa3febf1d2d7c8696a8515ce
+size 905987800

model-00013-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83909f2361e8e5e2fc759848d270e54a69018ccebf902257c0783a637d01282
+size 998253976

model-00014-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442a527abfc8ad99714c3a5b7c7b5991042aedd24507d7e6364a7591b2ff7b4e
+size 905979504

model-00015-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9168ff85a032a77a5897bd46536ac439df1489d9c31f46c7ae95dfa3d54741e6
+size 905987816

model-00016-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f9b73e67a105f0c7752cfdaa2d20d93246971d2ce601efe29500ef91f7e383
+size 905987816

model-00017-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a5250d32165fa1de95b4fb8c57911f34b9fa305bae59391aad01dc326ad1f5
+size 939525304

model-00018-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67e822afbc8ffc37f217b75ee7f4d58b4e17ef4e63c02e041ace7a938e442e1
+size 905987816

model-00019-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c339f784947dcacefdd0881699b56b9a4419e8db0edc022c46fadbc9e9ca14
+size 905987816

model-00020-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd90b1d9b7b4168cbb85d36eac40d12fa5705d5266e3e91d3bfd77c8eaa0383
+size 939525304

model-00021-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edde7d8d1e19b4d92d03bc471addba215b1298c46aa1b47b362d9bebce4c2e12
+size 905987816

model-00022-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e6282634f76aaeade80c91b7418481f423e8cfbb94f50530666d7e2eae6a2f
+size 905987816

model-00023-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef12e7c6e15b6bf50a4bc51dd290ae864527b627ce3d043a0b6cf5771d8fd4f0
+size 998253992

model-00024-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a856af912e547df7f6d8d594029e4dc1904f05bed6c583564d2dff363ae421
+size 905979512

model-00025-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66561a16a8a2b7d8ec5f9a4c6d97d28c18e5b7edaaabfc9faaf1467915a8db42
+size 905987816

model-00026-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542bd74095e78329b1366ea16d0abc702d4f7348d4271129d410d6d01e0513e5
+size 905987816

model-00027-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2ed548e98b816981a37ef0fc84430cf005ea41616d7955120d1a1e422419fd
+size 939525304

model-00028-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008d42c07bdc804d10a30a75e5774f0094065bed71178ada36e40987e9f35256
+size 905987816

model-00029-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b03a48cee3b9fb0efd94fcb421817ef151ae1ee4a54bf835c0158ce91d436b
+size 905987816

model-00030-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5352bc6e6e5bd0e780eaa47a36bcb14341c6513bea495e8a83073e5c1ed324d
+size 939525304

model-00031-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab9201af4683cfc47e32e1175baf3e99fa8288c880240d1cab7e8c21d60bd14
+size 905987816

model-00032-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1931b503433477ad7c41376cbf93c4b0ee3068a2681faa294c15dbac110744
+size 905987816

model-00033-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6dc63ee60e0f07d349d1b82374cec2d406e67a291791258f9ef54a0d47e69c
+size 998253992

model-00034-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72242e5bbfa8617aa94a8dd516eb6f5a66044f55a448d94cb0ee13c81273d1b7
+size 905979512

model-00035-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3538aa2a7155e7c207505d9e0dd753227cca1cd89f4a9cc963b1bcb9dfafefec
+size 905987816

model-00036-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5512934c40f15fbd3fca178b5b027ff7a60842106a9c7c27bce43c5897f68228
+size 905987816

model-00037-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e943a53a70327b280b62593754ff52c53477593e103c712ecc980af27a756f06
+size 939525304

model-00038-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca65ae07d5d34e8e6566c528fa883115958d6b0bca87fdc635aa877601d34da
+size 905987816

model-00039-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112c540dc959eca417109e4669681492f4ee14bccfff17b92a5f922d970ed770
+size 905987816

model-00040-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d8ad35e44ed205cb67a93429e06cbe98bb9e839fcef33e4162daa841ae3a6f
+size 939525304

model-00041-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b722e5d5cf898b2262c5a0fb591f456d85f3dea0a3350bf7e8ed9b8506627a
+size 905987816

model-00042-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca4f6848ff46d92ddea1e2c0208ccc924898aec42554b63416f82206539bb8d
+size 905987816

model-00043-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef5ba3c8ecc7dcb13d2f556b5270622e6bb82dc950aff99020a4531fc7c9e9b
+size 998253992

model-00044-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2020b5879b9158f8a355be4ea0e4fe869088b5ed09753d70d19820cedb5a7a
+size 905979512

model-00045-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff1df8427afe2976e659fe7f83da2afecc3ab915482a251491584920c7cc0de
+size 905987816

model-00046-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d21175be2b0f7fda8ab55abc447ecc79c47911df061ae03a21acb7821fad2de
+size 822092944

model-00047-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847f0c094ab7103be085db0a2b0acba2bc70292ccd2f0d097212f3e58217c73a
+size 263196472

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 42670235648}, "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.self_attn.q_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00047.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00047.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00047.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00047.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00047.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00047.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00047.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00047.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00047.safetensors", "model.layers.8.input_layernorm.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00047.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00047.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00047.safetensors", "model.layers.10.input_layernorm.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00047.safetensors", "model.layers.11.input_layernorm.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00016-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00047.safetensors", "model.layers.12.input_layernorm.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00047.safetensors", "model.layers.13.input_layernorm.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00019-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00047.safetensors", "model.layers.14.input_layernorm.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00047.safetensors", "model.layers.15.input_layernorm.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00022-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00047.safetensors", "model.layers.16.input_layernorm.weight": "model-00023-of-00047.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00047.safetensors", "model.layers.17.input_layernorm.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00047.safetensors", "model.layers.18.input_layernorm.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00026-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00047.safetensors", "model.layers.19.input_layernorm.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00047.safetensors", "model.layers.20.input_layernorm.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00029-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00047.safetensors", "model.layers.21.input_layernorm.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00047.safetensors", "model.layers.22.input_layernorm.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00032-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00047.safetensors", "model.layers.23.input_layernorm.weight": "model-00033-of-00047.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00047.safetensors", "model.layers.24.input_layernorm.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00047.safetensors", "model.layers.25.input_layernorm.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00036-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00047.safetensors", "model.layers.26.input_layernorm.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00047.safetensors", "model.layers.27.input_layernorm.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00039-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00047.safetensors", "model.layers.28.input_layernorm.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00042-of-00047.safetensors", "model.layers.29.input_layernorm.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00042-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00047.safetensors", "model.layers.30.input_layernorm.weight": "model-00043-of-00047.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00045-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00045-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00047.safetensors", "model.layers.31.input_layernorm.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00046-of-00047.safetensors", "model.norm.weight": "model-00046-of-00047.safetensors", "lm_head.weight": "model-00047-of-00047.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors"}}