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/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d9fee80d0cbd74ba5df4b368ba3df6077f469ac5 --- /dev/null +++ b/config.json @@ -0,0 +1,243 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 16384, + "initializer_range": 0.02, + "intermediate_size": 53248, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 128, + "num_hidden_layers": 126, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "quantization_config": { + "algo_config": { + "compute_scale_loss": "MAE", + "model_decoder_layers": "model.layers", + "name": "autosmoothquant", + "num_attention_heads": -1, + "num_key_value_heads": -1, + "scaling_layers": [ + { + "inp": "self_attn.q_proj", + "layers": [ + "self_attn.q_proj", + "self_attn.k_proj", + "self_attn.v_proj" + ], + "module2inspect": "self_attn", + "prev_op": "input_layernorm" + }, + { + "inp": "self_attn.o_proj", + "layers": [ + "self_attn.o_proj" + ], + "prev_op": "self_attn.v_proj" + }, + { + "inp": "mlp.gate_proj", + "layers": [ + "mlp.gate_proj", + "mlp.up_proj" + ], + "module2inspect": "mlp", + "prev_op": "post_attention_layernorm" + }, + { + "inp": "mlp.down_proj", + "layers": [ + "mlp.down_proj" + ], + "prev_op": "mlp.up_proj" + } + ] + }, + "exclude": [ + "lm_head" + ], + "export": { + "kv_cache_group": [ + "*k_proj", + "*v_proj" + ], + "min_kv_scale": 1.0, + "pack_method": "reorder", + "weight_format": "real_quantized", + "weight_merge_groups": null + }, + "global_quant_config": { + "bias": null, + "input_tensors": { + "ch_axis": -1, + "dtype": "fp4", + "group_size": 32, + "is_dynamic": true, + "is_mx_scale_constraint": false, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerBlockMXObserver", + "qscheme": "per_group", + "round_method": "half_even", + "scale_calculation_mode": "even", + "scale_format": "e8m0", + "scale_type": "float", + "symmetric": null + }, + "output_tensors": null, + "target_device": null, + "weight": { + "ch_axis": -1, + "dtype": "fp4", + "group_size": 32, + "is_dynamic": false, + "is_mx_scale_constraint": false, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerBlockMXObserver", + "qscheme": "per_group", + "round_method": "half_even", + "scale_calculation_mode": "even", + "scale_format": "e8m0", + "scale_type": "float", + "symmetric": null + } + }, + "layer_quant_config": { + "*k_proj": { + "bias": null, + "input_tensors": { + "ch_axis": -1, + "dtype": "fp4", + "group_size": 32, + "is_dynamic": true, + "is_mx_scale_constraint": false, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerBlockMXObserver", + "qscheme": "per_group", + "round_method": "half_even", + "scale_calculation_mode": "even", + "scale_format": "e8m0", + "scale_type": "float", + "symmetric": null + }, + "output_tensors": { + "ch_axis": null, + "dtype": "fp8_e4m3", + "group_size": null, + "is_dynamic": false, + "is_mx_scale_constraint": null, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerTensorMinMaxObserver", + "qscheme": "per_tensor", + "round_method": null, + "scale_calculation_mode": null, + "scale_format": null, + "scale_type": null, + "symmetric": null + }, + "target_device": null, + "weight": { + "ch_axis": -1, + "dtype": "fp4", + "group_size": 32, + "is_dynamic": false, + "is_mx_scale_constraint": false, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerBlockMXObserver", + "qscheme": "per_group", + "round_method": "half_even", + "scale_calculation_mode": "even", + "scale_format": "e8m0", + "scale_type": "float", + "symmetric": null + } + }, + "*v_proj": { + "bias": null, + "input_tensors": { + "ch_axis": -1, + "dtype": "fp4", + "group_size": 32, + "is_dynamic": true, + "is_mx_scale_constraint": false, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerBlockMXObserver", + "qscheme": "per_group", + "round_method": "half_even", + "scale_calculation_mode": "even", + "scale_format": "e8m0", + "scale_type": "float", + "symmetric": null + }, + "output_tensors": { + "ch_axis": null, + "dtype": "fp8_e4m3", + "group_size": null, + "is_dynamic": false, + "is_mx_scale_constraint": null, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerTensorMinMaxObserver", + "qscheme": "per_tensor", + "round_method": null, + "scale_calculation_mode": null, + "scale_format": null, + "scale_type": null, + "symmetric": null + }, + "target_device": null, + "weight": { + "ch_axis": -1, + "dtype": "fp4", + "group_size": 32, + "is_dynamic": false, + "is_mx_scale_constraint": false, + "is_scale_quant": false, + "mx_element_dtype": null, + "observer_cls": "PerBlockMXObserver", + "qscheme": "per_group", + "round_method": "half_even", + "scale_calculation_mode": "even", + "scale_format": "e8m0", + "scale_type": "float", + "symmetric": null + } + } + }, + "layer_type_quant_config": {}, + "quant_method": "quark", + "quant_mode": "eager_mode", + "softmax_quant_spec": null + }, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..2b8ae57a0d941ca239bd6c03b4660a3f29bc30a8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.51.3" +} diff --git a/model-00001-of-00047.safetensors b/model-00001-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df79fa4317a808e5ef47e5038665d745d9b83241 --- /dev/null +++ b/model-00001-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02bf1a1e4699210d66cc2344c1c544e71c9e79ac9e787cbc899751a27cb4de4d +size 4969203212 diff --git a/model-00002-of-00047.safetensors b/model-00002-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e6c7946d01fa4b9f061c37c7e298ce16f1af0a5 --- /dev/null +++ b/model-00002-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a11ef1cddd97b7934140639608c3da57e6131dd76dba7abd84779b644e86aa +size 4617082732 diff --git a/model-00003-of-00047.safetensors b/model-00003-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..040abd34b8da8515cd1ab77c381644a6be80fda6 --- /dev/null +++ b/model-00003-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743d0066c4f44fb55e98587995ab2516868616e7147599e3bab8f98f5b3bad47 +size 4937946980 diff --git a/model-00004-of-00047.safetensors b/model-00004-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8ed6c95ab66b724b76c11260a21fd393d266ffc --- /dev/null +++ b/model-00004-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3168f77dd774296f00d8ac7ad3072c4d2fc60ef351d10af042f050880a6f17d +size 4920120504 diff --git a/model-00005-of-00047.safetensors b/model-00005-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f28e845d52e0a97d9331d4aca7aad1c2d3a80a6b --- /dev/null +++ b/model-00005-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c2620f7f0668fd983fca774199e3fb3332e2a1c55eff9f5199ea0291ab1262 +size 4617016996 diff --git a/model-00006-of-00047.safetensors b/model-00006-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..37660c0c0a3b46d4a6b0650e7c340aef3eadc77e --- /dev/null +++ b/model-00006-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15abdfa5c5296a63fefc693343fa855bfd5b225919589245253c723b02873d30 +size 4617082788 diff --git a/model-00007-of-00047.safetensors b/model-00007-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0c7a7d6bc62b9962910e350009f1d7bf4894240 --- /dev/null +++ b/model-00007-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc30354e6ce6fd83230cd4854f0ce678112b133af2c286e6d202aa6ffed33bc4 +size 4617082780 diff --git a/model-00008-of-00047.safetensors b/model-00008-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bda7a9317f77bfd88a2b30619cc32026d964d972 --- /dev/null +++ b/model-00008-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2246996165e833a1e45161a41f1adebbc7a9cdc68f98315e2327ba949783c4f4 +size 4937947028 diff --git a/model-00009-of-00047.safetensors b/model-00009-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee34825ea03adbc1c7b4878c28ddcebbb91bd80b --- /dev/null +++ b/model-00009-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e163331174ee2d632b6ad924f66673e14e9fd45f40578463e877414f09c8abb8 +size 4920120544 diff --git a/model-00010-of-00047.safetensors b/model-00010-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..004a7c38dc469fdb4f237b54d1622f02dac4fcee --- /dev/null +++ b/model-00010-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3a94bc4a1d4519bc5e5c480fc800c2d46f7ea452a0d5c961eec81bc46c9a51 +size 4617017020 diff --git a/model-00011-of-00047.safetensors b/model-00011-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..40f9090fdef99802e1f4349131c98d9d39e0c650 --- /dev/null +++ b/model-00011-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4510f5f68ccccb63ce0008fa23b66526b26806148b20c3f1f611e78fc948204f +size 4617082788 diff --git a/model-00012-of-00047.safetensors b/model-00012-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d665222dccc3df6ee587d7220158da23e607d11 --- /dev/null +++ b/model-00012-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec168b662e462bb4324c19db090bc50c0777d7d250ee2c16c3febd9c90bce4f +size 4617082780 diff --git a/model-00013-of-00047.safetensors b/model-00013-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29155b626af17e8b2d73b55a21b6af81624b008c --- /dev/null +++ b/model-00013-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d2c71f40e4d1a78a6ebea45c4b34bca4449d933cfa16faf6776b810054323f +size 4937947028 diff --git a/model-00014-of-00047.safetensors b/model-00014-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bec692714cf193c0e9817a6583623e36c756770 --- /dev/null +++ b/model-00014-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e2ce7e618befa700c8d870de65f49298b72c15bb7184c07c53df58d970b95f5 +size 4920120544 diff --git a/model-00015-of-00047.safetensors b/model-00015-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..217b45270b6c11dfed3daa2b6c9de8cf1633f45a --- /dev/null +++ b/model-00015-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe95f4f618f40416b0a1bafe93abaede35f2a196bbb490f12f28cfe8f97b23a1 +size 4617017020 diff --git a/model-00016-of-00047.safetensors b/model-00016-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8724dc8ce66208f5b9b4ab0a7f27c56da855abf --- /dev/null +++ b/model-00016-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2380dbe52f7c7619f6035d10d84f6bc5bc1834d334752529ba6b9cbd3544f2cd +size 4617082788 diff --git a/model-00017-of-00047.safetensors b/model-00017-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c77a14f19bbea056ff858da72710cf4e2dfca251 --- /dev/null +++ b/model-00017-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d189e454e830306f3bfd33f82811519c09d558838f0e8c258b5a73ee4130329 +size 4617082780 diff --git a/model-00018-of-00047.safetensors b/model-00018-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99b5831bc2b633c8e313bc3073297773cad53e35 --- /dev/null +++ b/model-00018-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c74d97bf51275b4889d934630e7f74ef85000e8a9bfc12f486239fa0edff515 +size 4937947028 diff --git a/model-00019-of-00047.safetensors b/model-00019-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2073df62ff9ed04e59f2e6008b950abc312adbc --- /dev/null +++ b/model-00019-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d989b87d0afdf206f9d645e652a96f8cd4ab5a798ca368297792ded371e1644 +size 4920120544 diff --git a/model-00020-of-00047.safetensors b/model-00020-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..792b6b64f30c4d6857f5ee72e126130a3ad87d17 --- /dev/null +++ b/model-00020-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5a5a84d5feb6a250d1b1814f46a44d42d3345dc46366d4e1df44521863958f +size 4617017020 diff --git a/model-00021-of-00047.safetensors b/model-00021-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b077e6e06c2adf8dea7adf93e59d43dcc26d5be --- /dev/null +++ b/model-00021-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60f2b8213a35fad970807f8517c09be606b6b750b9fe3be762d300626a133763 +size 4617082788 diff --git a/model-00022-of-00047.safetensors b/model-00022-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d22417a819c4bcfee0c8eafcdf7bbee942d185d9 --- /dev/null +++ b/model-00022-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b733f47f71a6cdad19fcb83105a9ec870f733e306435f477b7a53dea88816f2b +size 4617082780 diff --git a/model-00023-of-00047.safetensors b/model-00023-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..edcc526bc10b47c923106471ba65bc42d380fd6c --- /dev/null +++ b/model-00023-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c270b66a18b33bc2801fbb81e242debf5e1720a7a455aa610c3572216d5b99 +size 4937947028 diff --git a/model-00024-of-00047.safetensors b/model-00024-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..adb5b47363f7a04192e4b235572c39eb9292c2c3 --- /dev/null +++ b/model-00024-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dcaeecd9c57e13c4ca63d4afbb3f20b4cf9ee7acbf6524e3b2883971f6da157 +size 4920120544 diff --git a/model-00025-of-00047.safetensors b/model-00025-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5800abe46864b423ab08be9bed1c0e335c11ea0 --- /dev/null +++ b/model-00025-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c37728d0ee7fe6671c6575e4c41bb1d63cad3b1dff59a7c080268e37f8a9b782 +size 4617017020 diff --git a/model-00026-of-00047.safetensors b/model-00026-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb3bdd8d3a12a0e40b26b7ce986f0186f103f96f --- /dev/null +++ b/model-00026-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:508c0f748524a5eb06e10d5f3e9f81f1b8735ca32ed57c25a2796224010e1aea +size 4617082788 diff --git a/model-00027-of-00047.safetensors b/model-00027-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86c4ee7f2362c5211cbff4a7a2c7859817748d83 --- /dev/null +++ b/model-00027-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba15491a6622571e5777bb36c2c972e5c67235bf9b793ce3282e0f771ec7670e +size 4617082780 diff --git a/model-00028-of-00047.safetensors b/model-00028-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56cc6f91c101ccfa241cca6cfad4fa572b4621df --- /dev/null +++ b/model-00028-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a47911b980bc5e26f8ede7d07c3aaf82ae8bb6bf78f325c9f8ba171c032033b +size 4937947028 diff --git a/model-00029-of-00047.safetensors b/model-00029-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66a3895c5885ca58efd3379768e33f52eab37e04 --- /dev/null +++ b/model-00029-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e262206c8ec8f9628a0bcd02cf5624813283f0d88032d98812d2c12128499211 +size 4920120544 diff --git a/model-00030-of-00047.safetensors b/model-00030-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8af2e7542c91d5a7f9f1888c526d61b7d3cef37d --- /dev/null +++ b/model-00030-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d676b442c7ad005c0817b6eac0ae8022538d722ccc954d8730119c9edbf0c3f2 +size 4617017020 diff --git a/model-00031-of-00047.safetensors b/model-00031-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..72d9c647f6fc441050e656e7db2421d4ec50c9ca --- /dev/null +++ b/model-00031-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b470887648c61fcf6e305e088f9b49d95a7286ab05310ff413fc47573310792 +size 4617082788 diff --git a/model-00032-of-00047.safetensors b/model-00032-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5ea12f1f8915a94c00f9fec07cb2ecc10ae8510 --- /dev/null +++ b/model-00032-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8553c4745d4dd94e3295c825a7ef66ea5008c22635a5bad4e221b0fc58e1e9 +size 4617082780 diff --git a/model-00033-of-00047.safetensors b/model-00033-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4afce45ef87ed75284faf48c5c74190c942c1bac --- /dev/null +++ b/model-00033-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e9927835f13b29e0d1dcbd982ebe191faadbf649c3a7c592e27994f68c3973 +size 4937947028 diff --git a/model-00034-of-00047.safetensors b/model-00034-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36e115d9306da3c33b64709b60b028a1814394e6 --- /dev/null +++ b/model-00034-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b058f465d0e9bca11666740db5c186d910ffc42245e7f48edcb893e1fa860c +size 4920120544 diff --git a/model-00035-of-00047.safetensors b/model-00035-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11b415b3a80b79db96de76e1c60c3f01a1527ba2 --- /dev/null +++ b/model-00035-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c61d18db72e07f2869973d184018ec5792682470b8a30dc3e0fb3c6a7cc6ac5 +size 4617017020 diff --git a/model-00036-of-00047.safetensors b/model-00036-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4adbea3c285b67167af36da90218e6b1cc8854b3 --- /dev/null +++ b/model-00036-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f9e821929e1e5540b98fee081122af3c4332665acaaa0edee1e41107bb63c9 +size 4617082788 diff --git a/model-00037-of-00047.safetensors b/model-00037-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf3b77e3c77195a793bda7f7c51ce963a8d3d9aa --- /dev/null +++ b/model-00037-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e535f0ed5b823861abf6489ac458fc5568f677c6b9f84e9706be4cc5a534c89 +size 4617082804 diff --git a/model-00038-of-00047.safetensors b/model-00038-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b881044eedc5af74780899f0b806b02536809178 --- /dev/null +++ b/model-00038-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7db7ff43e025ae60c5a9d66d1a914649eacd3cd7ae47f18923d4cec1a75af6 +size 4937947084 diff --git a/model-00039-of-00047.safetensors b/model-00039-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8915c150a254d22df3ea310471236cc6b2027e2a --- /dev/null +++ b/model-00039-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587afb2c4ea505f3060355464b0057417e2992e42407934bf94865ccc3ef2bfc +size 4920120592 diff --git a/model-00040-of-00047.safetensors b/model-00040-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..499207005b506af2281d00ad09875460f80e71bb --- /dev/null +++ b/model-00040-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3217a0c61534ba894056e506cc51c37ea834542f0238bc45c7304846e1abb5cd +size 4617017068 diff --git a/model-00041-of-00047.safetensors b/model-00041-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe22ad98c22910a04878dade7cae281a59598021 --- /dev/null +++ b/model-00041-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca9a1511991fe49d227fe5d49f9bcd0bf03744f701032d4b45c3edba8ef1397 +size 4617082836 diff --git a/model-00042-of-00047.safetensors b/model-00042-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24b6326dac543a2869092f89e3dd5f37af19ecc2 --- /dev/null +++ b/model-00042-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26cd4b886143282e6282fc6500e379e9ff24ec780db996036365bd36620fa0ec +size 4617082836 diff --git a/model-00043-of-00047.safetensors b/model-00043-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f291884e3852b072421fc1ac6df9a434b2952da --- /dev/null +++ b/model-00043-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98654b60a90825d725241ed7c729668ed12013302080a85f697b4ea65a4188ec +size 4937947084 diff --git a/model-00044-of-00047.safetensors b/model-00044-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1866f4805f73aa2cb93111e01190517c9aea44cc --- /dev/null +++ b/model-00044-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f1d54ecc74fbc32b29b33e9c42c647b2e58a277cd60f578e40f1d59b52de362 +size 4920120592 diff --git a/model-00045-of-00047.safetensors b/model-00045-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22cf331d9c53b2a72c6bed987f3aeb6073697583 --- /dev/null +++ b/model-00045-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c06902c41afe52138cc19814ce4034987bcd4bc67ddf81f211a3a0273c25fa +size 4617017068 diff --git a/model-00046-of-00047.safetensors b/model-00046-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..588948d918d4415041c4cd69a08526e338a7d30b --- /dev/null +++ b/model-00046-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a80e41751d3f6cedf07ffac89af3d2e3150cd9cfd365d173a85d309f80f65a2 +size 3850605216 diff --git a/model-00047-of-00047.safetensors b/model-00047-of-00047.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..189b2ba970360412785980a181e8aa7ae7624a18 --- /dev/null +++ b/model-00047-of-00047.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b079a02069ebe5a5f4f8135815f136afb1d6fc4423620dcb2a14fa399cdf12 +size 4202692736 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..602eaa927e7f6d8fc02750cc051f1a977993765e --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,2278 @@ +{ + "metadata": { + "total_size": 221788406264 + }, + "weight_map": { + "lm_head.weight": "model-00047-of-00047.safetensors", + "model.embed_tokens.weight": "model-00001-of-00047.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.0.mlp.down_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00047.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.0.mlp.up_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.0.self_attn.k_proj.output_scale": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.v_proj.output_scale": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00047.safetensors", + "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00047.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.down_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.gate_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.mlp.up_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.k_proj.output_scale": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.k_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.o_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.q_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.v_proj.output_scale": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.1.self_attn.v_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.10.input_layernorm.weight": "model-00005-of-00047.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.10.mlp.down_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.10.mlp.gate_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.10.mlp.up_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.k_proj.output_scale": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.k_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.o_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.q_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.v_proj.output_scale": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.10.self_attn.v_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.100.input_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.100.mlp.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.100.mlp.down_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.100.mlp.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.100.mlp.gate_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.100.mlp.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.100.mlp.up_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.100.post_attention_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.k_proj.output_scale": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.k_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.k_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.o_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.o_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.q_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.q_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.v_proj.output_scale": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.v_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.100.self_attn.v_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.101.input_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.101.mlp.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.101.mlp.down_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.101.mlp.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.101.mlp.gate_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.101.mlp.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.101.mlp.up_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.101.post_attention_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.101.self_attn.k_proj.output_scale": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.k_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.k_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.o_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.o_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.q_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.q_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.v_proj.output_scale": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.v_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.101.self_attn.v_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.102.input_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.102.mlp.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.102.mlp.down_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.102.mlp.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.102.mlp.gate_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.102.mlp.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.102.mlp.up_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.102.post_attention_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.k_proj.output_scale": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.k_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.k_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.o_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.o_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.q_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.q_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.v_proj.output_scale": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.v_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.102.self_attn.v_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.103.input_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.103.mlp.down_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.103.mlp.down_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.103.mlp.gate_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.103.mlp.gate_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.103.mlp.up_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.103.mlp.up_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.103.post_attention_layernorm.weight": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.k_proj.output_scale": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.k_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.k_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.o_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.o_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.q_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.q_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.v_proj.output_scale": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.v_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.103.self_attn.v_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.104.input_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.104.mlp.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.104.mlp.down_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.104.mlp.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.104.mlp.gate_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.104.mlp.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.104.mlp.up_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.104.post_attention_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.104.self_attn.k_proj.output_scale": "model-00038-of-00047.safetensors", + "model.layers.104.self_attn.k_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.104.self_attn.k_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.104.self_attn.o_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.104.self_attn.o_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.104.self_attn.q_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.104.self_attn.q_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.104.self_attn.v_proj.output_scale": "model-00038-of-00047.safetensors", + "model.layers.104.self_attn.v_proj.weight": "model-00038-of-00047.safetensors", + "model.layers.104.self_attn.v_proj.weight_scale": "model-00038-of-00047.safetensors", + "model.layers.105.input_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.105.mlp.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.105.mlp.down_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.105.mlp.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.105.mlp.gate_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.105.mlp.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.105.mlp.up_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.105.post_attention_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.k_proj.output_scale": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.k_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.k_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.o_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.o_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.q_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.q_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.v_proj.output_scale": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.v_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.105.self_attn.v_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.106.input_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.106.mlp.down_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.106.mlp.down_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.106.mlp.gate_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.106.mlp.gate_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.106.mlp.up_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.106.mlp.up_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.106.post_attention_layernorm.weight": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.k_proj.output_scale": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.k_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.k_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.o_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.o_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.q_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.q_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.v_proj.output_scale": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.v_proj.weight": "model-00039-of-00047.safetensors", + "model.layers.106.self_attn.v_proj.weight_scale": "model-00039-of-00047.safetensors", + "model.layers.107.input_layernorm.weight": "model-00040-of-00047.safetensors", + "model.layers.107.mlp.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.107.mlp.down_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.107.mlp.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.107.mlp.gate_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.107.mlp.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.107.mlp.up_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.107.post_attention_layernorm.weight": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.k_proj.output_scale": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.k_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.k_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.o_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.o_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.q_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.q_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.v_proj.output_scale": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.v_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.107.self_attn.v_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.108.input_layernorm.weight": "model-00040-of-00047.safetensors", + "model.layers.108.mlp.down_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.108.mlp.down_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.108.mlp.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.108.mlp.gate_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.108.mlp.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.108.mlp.up_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.108.post_attention_layernorm.weight": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.k_proj.output_scale": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.k_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.k_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.o_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.o_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.q_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.q_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.v_proj.output_scale": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.v_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.108.self_attn.v_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.109.input_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.109.mlp.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.109.mlp.down_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.109.mlp.gate_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.109.mlp.gate_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.109.mlp.up_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.109.mlp.up_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.109.post_attention_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.109.self_attn.k_proj.output_scale": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.k_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.k_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.o_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.o_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.q_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.q_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.v_proj.output_scale": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.v_proj.weight": "model-00040-of-00047.safetensors", + "model.layers.109.self_attn.v_proj.weight_scale": "model-00040-of-00047.safetensors", + "model.layers.11.input_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.11.mlp.down_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.11.mlp.gate_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.11.mlp.up_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.11.self_attn.k_proj.output_scale": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.k_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.o_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.q_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.v_proj.output_scale": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.11.self_attn.v_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.110.input_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.110.mlp.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.110.mlp.down_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.110.mlp.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.110.mlp.gate_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.110.mlp.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.110.mlp.up_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.110.post_attention_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.k_proj.output_scale": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.k_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.k_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.o_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.o_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.q_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.q_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.v_proj.output_scale": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.v_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.110.self_attn.v_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.111.input_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.111.mlp.down_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.111.mlp.down_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.111.mlp.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.111.mlp.gate_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.111.mlp.up_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.111.mlp.up_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.111.post_attention_layernorm.weight": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.k_proj.output_scale": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.k_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.k_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.o_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.o_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.q_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.q_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.v_proj.output_scale": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.v_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.111.self_attn.v_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.112.input_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.112.mlp.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.112.mlp.down_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.112.mlp.gate_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.112.mlp.gate_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.112.mlp.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.112.mlp.up_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.112.post_attention_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.112.self_attn.k_proj.output_scale": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.k_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.k_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.o_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.o_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.q_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.v_proj.output_scale": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00047.safetensors", + "model.layers.112.self_attn.v_proj.weight_scale": "model-00041-of-00047.safetensors", + "model.layers.113.input_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.113.mlp.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.113.mlp.down_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.113.mlp.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.113.mlp.gate_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.113.mlp.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.113.mlp.up_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.113.post_attention_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.k_proj.output_scale": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.k_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.k_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.o_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.o_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.q_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.q_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.v_proj.output_scale": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.v_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.113.self_attn.v_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.114.input_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.114.mlp.down_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.114.mlp.down_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.114.mlp.gate_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.114.mlp.gate_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.114.mlp.up_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.114.mlp.up_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.114.post_attention_layernorm.weight": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.k_proj.output_scale": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.k_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.k_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.o_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.o_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.q_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.q_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.v_proj.output_scale": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.v_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.114.self_attn.v_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.115.input_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.115.mlp.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.115.mlp.down_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.115.mlp.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.115.mlp.gate_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.115.mlp.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.115.mlp.up_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.115.post_attention_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.115.self_attn.k_proj.output_scale": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.k_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.k_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.o_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.o_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.q_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.q_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.v_proj.output_scale": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.v_proj.weight": "model-00042-of-00047.safetensors", + "model.layers.115.self_attn.v_proj.weight_scale": "model-00042-of-00047.safetensors", + "model.layers.116.input_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.116.mlp.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.116.mlp.down_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.116.mlp.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.116.mlp.gate_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.116.mlp.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.116.mlp.up_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.116.post_attention_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.k_proj.output_scale": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.k_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.k_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.o_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.o_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.q_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.q_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.v_proj.output_scale": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.v_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.116.self_attn.v_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.117.input_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.117.mlp.down_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.117.mlp.down_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.117.mlp.gate_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.117.mlp.gate_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.117.mlp.up_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.117.mlp.up_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.117.post_attention_layernorm.weight": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.k_proj.output_scale": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.k_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.k_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.o_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.o_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.q_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.q_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.v_proj.output_scale": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.v_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.117.self_attn.v_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.118.input_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.118.mlp.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.118.mlp.down_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.118.mlp.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.118.mlp.gate_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.118.mlp.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.118.mlp.up_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.118.post_attention_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.118.self_attn.k_proj.output_scale": "model-00043-of-00047.safetensors", + "model.layers.118.self_attn.k_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.118.self_attn.k_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.118.self_attn.o_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.118.self_attn.o_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.118.self_attn.q_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.118.self_attn.q_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.118.self_attn.v_proj.output_scale": "model-00043-of-00047.safetensors", + "model.layers.118.self_attn.v_proj.weight": "model-00043-of-00047.safetensors", + "model.layers.118.self_attn.v_proj.weight_scale": "model-00043-of-00047.safetensors", + "model.layers.119.input_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.119.mlp.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.119.mlp.down_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.119.mlp.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.119.mlp.gate_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.119.mlp.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.119.mlp.up_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.119.post_attention_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.k_proj.output_scale": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.k_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.k_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.o_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.o_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.q_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.q_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.v_proj.output_scale": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.v_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.119.self_attn.v_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.12.input_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.12.mlp.down_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.12.mlp.gate_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.12.mlp.up_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.k_proj.output_scale": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.k_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.o_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.q_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.v_proj.output_scale": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.12.self_attn.v_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.120.input_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.120.mlp.down_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.120.mlp.down_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.120.mlp.gate_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.120.mlp.gate_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.120.mlp.up_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.120.mlp.up_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.120.post_attention_layernorm.weight": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.k_proj.output_scale": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.k_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.k_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.o_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.o_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.q_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.q_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.v_proj.output_scale": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.v_proj.weight": "model-00044-of-00047.safetensors", + "model.layers.120.self_attn.v_proj.weight_scale": "model-00044-of-00047.safetensors", + "model.layers.121.input_layernorm.weight": "model-00045-of-00047.safetensors", + "model.layers.121.mlp.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.121.mlp.down_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.121.mlp.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.121.mlp.gate_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.121.mlp.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.121.mlp.up_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.121.post_attention_layernorm.weight": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.k_proj.output_scale": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.k_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.k_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.o_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.o_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.q_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.q_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.v_proj.output_scale": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.v_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.121.self_attn.v_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.122.input_layernorm.weight": "model-00045-of-00047.safetensors", + "model.layers.122.mlp.down_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.122.mlp.down_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.122.mlp.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.122.mlp.gate_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.122.mlp.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.122.mlp.up_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.122.post_attention_layernorm.weight": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.k_proj.output_scale": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.k_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.k_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.o_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.o_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.q_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.q_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.v_proj.output_scale": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.v_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.122.self_attn.v_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.123.input_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.123.mlp.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.123.mlp.down_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.123.mlp.gate_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.123.mlp.gate_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.123.mlp.up_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.123.mlp.up_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.123.post_attention_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.123.self_attn.k_proj.output_scale": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.k_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.k_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.o_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.o_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.q_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.q_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.v_proj.output_scale": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.v_proj.weight": "model-00045-of-00047.safetensors", + "model.layers.123.self_attn.v_proj.weight_scale": "model-00045-of-00047.safetensors", + "model.layers.124.input_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.124.mlp.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.124.mlp.down_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.124.mlp.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.124.mlp.gate_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.124.mlp.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.124.mlp.up_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.124.post_attention_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.k_proj.output_scale": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.k_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.k_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.o_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.o_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.q_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.q_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.v_proj.output_scale": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.v_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.124.self_attn.v_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.125.input_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.125.mlp.down_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.125.mlp.down_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.125.mlp.gate_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.125.mlp.gate_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.125.mlp.up_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.125.mlp.up_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.125.post_attention_layernorm.weight": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.k_proj.output_scale": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.k_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.k_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.o_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.o_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.q_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.q_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.v_proj.output_scale": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.v_proj.weight": "model-00046-of-00047.safetensors", + "model.layers.125.self_attn.v_proj.weight_scale": "model-00046-of-00047.safetensors", + "model.layers.13.input_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.13.mlp.down_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.13.mlp.gate_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.13.mlp.up_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.k_proj.output_scale": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.v_proj.output_scale": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.14.input_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.14.mlp.down_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.14.mlp.gate_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.14.mlp.up_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.14.self_attn.k_proj.output_scale": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.k_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.o_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.q_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.v_proj.output_scale": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00047.safetensors", + "model.layers.14.self_attn.v_proj.weight_scale": "model-00006-of-00047.safetensors", + "model.layers.15.input_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.15.mlp.down_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.15.mlp.gate_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.15.mlp.up_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.k_proj.output_scale": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.k_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.o_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.q_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.v_proj.output_scale": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.15.self_attn.v_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.16.input_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.16.mlp.down_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.16.mlp.gate_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.16.mlp.up_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.k_proj.output_scale": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.k_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.o_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.q_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.v_proj.output_scale": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.16.self_attn.v_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.17.input_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.17.mlp.down_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.17.mlp.gate_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.17.mlp.up_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.17.self_attn.k_proj.output_scale": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.k_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.o_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.q_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.v_proj.output_scale": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00047.safetensors", + "model.layers.17.self_attn.v_proj.weight_scale": "model-00007-of-00047.safetensors", + "model.layers.18.input_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.18.mlp.down_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.18.mlp.gate_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.18.mlp.up_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.k_proj.output_scale": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.k_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.o_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.q_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.v_proj.output_scale": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.18.self_attn.v_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.19.input_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.19.mlp.down_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.19.mlp.gate_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.19.mlp.up_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.k_proj.output_scale": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.k_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.o_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.q_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.v_proj.output_scale": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.19.self_attn.v_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.mlp.down_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.mlp.gate_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.mlp.up_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.k_proj.output_scale": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.k_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.o_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.q_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.v_proj.output_scale": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.2.self_attn.v_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.20.input_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.20.mlp.down_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.20.mlp.gate_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.20.mlp.up_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.20.self_attn.k_proj.output_scale": "model-00008-of-00047.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.20.self_attn.k_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.20.self_attn.o_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.20.self_attn.q_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.20.self_attn.v_proj.output_scale": "model-00008-of-00047.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00047.safetensors", + "model.layers.20.self_attn.v_proj.weight_scale": "model-00008-of-00047.safetensors", + "model.layers.21.input_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.21.mlp.down_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.21.mlp.gate_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.21.mlp.up_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.k_proj.output_scale": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.k_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.o_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.q_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.v_proj.output_scale": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.21.self_attn.v_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.22.input_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.22.mlp.down_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.22.mlp.gate_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.22.mlp.up_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.k_proj.output_scale": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.k_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.o_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.q_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.v_proj.output_scale": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00047.safetensors", + "model.layers.22.self_attn.v_proj.weight_scale": "model-00009-of-00047.safetensors", + "model.layers.23.input_layernorm.weight": "model-00010-of-00047.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.23.mlp.down_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.23.mlp.gate_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.23.mlp.up_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.k_proj.output_scale": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.k_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.o_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.q_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.v_proj.output_scale": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.23.self_attn.v_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.24.input_layernorm.weight": "model-00010-of-00047.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.24.mlp.down_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.24.mlp.gate_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.24.mlp.up_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.k_proj.output_scale": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.k_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.o_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.q_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.v_proj.output_scale": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.24.self_attn.v_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.25.input_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.25.mlp.down_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.25.mlp.gate_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.25.mlp.up_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.25.self_attn.k_proj.output_scale": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.k_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.o_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.q_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.v_proj.output_scale": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00047.safetensors", + "model.layers.25.self_attn.v_proj.weight_scale": "model-00010-of-00047.safetensors", + "model.layers.26.input_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.26.mlp.down_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.26.mlp.gate_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.26.mlp.up_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.k_proj.output_scale": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.k_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.o_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.q_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.v_proj.output_scale": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.26.self_attn.v_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.27.input_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.27.mlp.down_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.27.mlp.gate_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.27.mlp.up_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.k_proj.output_scale": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.v_proj.output_scale": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.28.input_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.28.mlp.down_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.28.mlp.gate_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.28.mlp.up_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.28.self_attn.k_proj.output_scale": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.k_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.o_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.q_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.v_proj.output_scale": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00047.safetensors", + "model.layers.28.self_attn.v_proj.weight_scale": "model-00011-of-00047.safetensors", + "model.layers.29.input_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.29.mlp.down_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.29.mlp.gate_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.29.mlp.up_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.k_proj.output_scale": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.k_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.o_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.q_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.v_proj.output_scale": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.29.self_attn.v_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.3.mlp.down_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.3.mlp.gate_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.3.mlp.up_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.3.self_attn.k_proj.output_scale": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.k_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.o_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.q_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.v_proj.output_scale": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00047.safetensors", + "model.layers.3.self_attn.v_proj.weight_scale": "model-00002-of-00047.safetensors", + "model.layers.30.input_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.30.mlp.down_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.30.mlp.gate_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.30.mlp.up_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.k_proj.output_scale": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.k_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.o_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.q_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.v_proj.output_scale": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.30.self_attn.v_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.31.input_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.31.mlp.down_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.31.mlp.gate_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.31.mlp.up_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.31.self_attn.k_proj.output_scale": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.k_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.o_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.q_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.v_proj.output_scale": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00047.safetensors", + "model.layers.31.self_attn.v_proj.weight_scale": "model-00012-of-00047.safetensors", + "model.layers.32.input_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.32.mlp.down_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.32.mlp.gate_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.32.mlp.up_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.k_proj.output_scale": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.k_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.o_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.q_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.v_proj.output_scale": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.32.self_attn.v_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.33.input_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.33.mlp.down_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.33.mlp.gate_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.33.mlp.up_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.k_proj.output_scale": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.k_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.o_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.q_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.v_proj.output_scale": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.33.self_attn.v_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.34.input_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.34.mlp.down_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.34.mlp.gate_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.34.mlp.up_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.34.self_attn.k_proj.output_scale": "model-00013-of-00047.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.34.self_attn.k_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.34.self_attn.o_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.34.self_attn.q_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.34.self_attn.v_proj.output_scale": "model-00013-of-00047.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00047.safetensors", + "model.layers.34.self_attn.v_proj.weight_scale": "model-00013-of-00047.safetensors", + "model.layers.35.input_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.35.mlp.down_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.35.mlp.gate_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.35.mlp.up_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.k_proj.output_scale": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.k_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.o_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.q_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.v_proj.output_scale": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.35.self_attn.v_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.36.input_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.36.mlp.down_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.36.mlp.gate_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.36.mlp.up_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.k_proj.output_scale": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.k_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.o_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.q_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.v_proj.output_scale": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00047.safetensors", + "model.layers.36.self_attn.v_proj.weight_scale": "model-00014-of-00047.safetensors", + "model.layers.37.input_layernorm.weight": "model-00015-of-00047.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.37.mlp.down_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.37.mlp.gate_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.37.mlp.up_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.k_proj.output_scale": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.k_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.o_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.q_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.v_proj.output_scale": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.37.self_attn.v_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.38.input_layernorm.weight": "model-00015-of-00047.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.38.mlp.down_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.38.mlp.gate_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.38.mlp.up_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.k_proj.output_scale": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.k_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.o_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.q_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.v_proj.output_scale": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.38.self_attn.v_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.39.input_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.39.mlp.down_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.39.mlp.gate_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.39.mlp.up_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.39.self_attn.k_proj.output_scale": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.k_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.o_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.q_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.v_proj.output_scale": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00047.safetensors", + "model.layers.39.self_attn.v_proj.weight_scale": "model-00015-of-00047.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.4.mlp.down_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.4.mlp.gate_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.4.mlp.up_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.k_proj.output_scale": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.k_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.o_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.q_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.v_proj.output_scale": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.4.self_attn.v_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.40.input_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.40.mlp.down_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.40.mlp.gate_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.40.mlp.up_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.k_proj.output_scale": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.k_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.o_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.q_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.v_proj.output_scale": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.40.self_attn.v_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.41.input_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.41.mlp.down_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.41.mlp.gate_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.41.mlp.up_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.k_proj.output_scale": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.k_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.o_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.q_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.v_proj.output_scale": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.41.self_attn.v_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.42.input_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.42.mlp.down_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.42.mlp.gate_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.42.mlp.up_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.42.self_attn.k_proj.output_scale": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.k_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.o_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.q_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.v_proj.output_scale": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00047.safetensors", + "model.layers.42.self_attn.v_proj.weight_scale": "model-00016-of-00047.safetensors", + "model.layers.43.input_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.43.mlp.down_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.43.mlp.gate_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.43.mlp.up_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.k_proj.output_scale": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.k_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.o_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.q_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.v_proj.output_scale": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.43.self_attn.v_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.44.input_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.44.mlp.down_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.44.mlp.gate_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.44.mlp.up_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.k_proj.output_scale": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.k_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.o_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.q_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.v_proj.output_scale": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.44.self_attn.v_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.45.input_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.45.mlp.down_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.45.mlp.gate_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.45.mlp.up_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.45.self_attn.k_proj.output_scale": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.k_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.o_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.q_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.v_proj.output_scale": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00047.safetensors", + "model.layers.45.self_attn.v_proj.weight_scale": "model-00017-of-00047.safetensors", + "model.layers.46.input_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.46.mlp.down_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.46.mlp.gate_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.46.mlp.up_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.k_proj.output_scale": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.k_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.o_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.q_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.v_proj.output_scale": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.46.self_attn.v_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.47.input_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.47.mlp.down_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.47.mlp.gate_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.47.mlp.up_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.k_proj.output_scale": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.k_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.o_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.q_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.v_proj.output_scale": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.47.self_attn.v_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.48.input_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.48.mlp.down_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.48.mlp.gate_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.48.mlp.up_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.48.self_attn.k_proj.output_scale": "model-00018-of-00047.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.48.self_attn.k_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.48.self_attn.o_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.48.self_attn.q_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.48.self_attn.v_proj.output_scale": "model-00018-of-00047.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00047.safetensors", + "model.layers.48.self_attn.v_proj.weight_scale": "model-00018-of-00047.safetensors", + "model.layers.49.input_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.49.mlp.down_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.49.mlp.gate_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.49.mlp.up_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.k_proj.output_scale": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.k_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.o_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.q_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.v_proj.output_scale": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.49.self_attn.v_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.5.mlp.down_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.5.mlp.gate_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.5.mlp.up_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.k_proj.output_scale": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.k_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.o_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.q_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.v_proj.output_scale": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.5.self_attn.v_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.50.input_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.50.mlp.down_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.50.mlp.gate_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.50.mlp.up_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.k_proj.output_scale": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.k_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.o_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.q_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.v_proj.output_scale": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00047.safetensors", + "model.layers.50.self_attn.v_proj.weight_scale": "model-00019-of-00047.safetensors", + "model.layers.51.input_layernorm.weight": "model-00020-of-00047.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.51.mlp.down_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.51.mlp.gate_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.51.mlp.up_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.k_proj.output_scale": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.k_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.o_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.q_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.v_proj.output_scale": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.51.self_attn.v_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.52.input_layernorm.weight": "model-00020-of-00047.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.52.mlp.down_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.52.mlp.gate_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.52.mlp.up_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.k_proj.output_scale": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.k_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.o_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.q_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.v_proj.output_scale": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.52.self_attn.v_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.53.input_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.53.mlp.down_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.53.mlp.gate_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.53.mlp.up_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.53.self_attn.k_proj.output_scale": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.k_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.o_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.q_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.v_proj.output_scale": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00047.safetensors", + "model.layers.53.self_attn.v_proj.weight_scale": "model-00020-of-00047.safetensors", + "model.layers.54.input_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.54.mlp.down_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.54.mlp.gate_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.54.mlp.up_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.k_proj.output_scale": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.k_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.o_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.q_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.v_proj.output_scale": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.54.self_attn.v_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.55.input_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.55.mlp.down_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.55.mlp.gate_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.55.mlp.up_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.k_proj.output_scale": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.k_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.o_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.q_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.v_proj.output_scale": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.55.self_attn.v_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.56.input_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.56.mlp.down_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.56.mlp.gate_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.56.mlp.up_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.56.self_attn.k_proj.output_scale": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.k_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.o_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.q_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.v_proj.output_scale": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00047.safetensors", + "model.layers.56.self_attn.v_proj.weight_scale": "model-00021-of-00047.safetensors", + "model.layers.57.input_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.57.mlp.down_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.57.mlp.gate_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.57.mlp.up_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.k_proj.output_scale": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.k_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.o_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.q_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.v_proj.output_scale": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.57.self_attn.v_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.58.input_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.58.mlp.down_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.58.mlp.gate_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.58.mlp.up_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.k_proj.output_scale": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.k_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.o_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.q_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.v_proj.output_scale": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.58.self_attn.v_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.59.input_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.59.mlp.down_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.59.mlp.gate_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.59.mlp.up_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.59.self_attn.k_proj.output_scale": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.k_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.o_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.q_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.v_proj.output_scale": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00047.safetensors", + "model.layers.59.self_attn.v_proj.weight_scale": "model-00022-of-00047.safetensors", + "model.layers.6.input_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.6.mlp.down_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.6.mlp.gate_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.6.mlp.up_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.6.self_attn.k_proj.output_scale": "model-00003-of-00047.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.6.self_attn.k_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.6.self_attn.o_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.6.self_attn.q_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.6.self_attn.v_proj.output_scale": "model-00003-of-00047.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00047.safetensors", + "model.layers.6.self_attn.v_proj.weight_scale": "model-00003-of-00047.safetensors", + "model.layers.60.input_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.60.mlp.down_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.60.mlp.gate_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.60.mlp.up_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.k_proj.output_scale": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.k_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.o_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.q_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.v_proj.output_scale": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.60.self_attn.v_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.61.input_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.61.mlp.down_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.61.mlp.gate_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.61.mlp.up_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.k_proj.output_scale": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.k_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.o_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.q_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.v_proj.output_scale": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.61.self_attn.v_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.62.input_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.62.mlp.down_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.62.mlp.gate_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.62.mlp.up_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.62.self_attn.k_proj.output_scale": "model-00023-of-00047.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.62.self_attn.k_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.62.self_attn.o_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.62.self_attn.q_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.62.self_attn.v_proj.output_scale": "model-00023-of-00047.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00047.safetensors", + "model.layers.62.self_attn.v_proj.weight_scale": "model-00023-of-00047.safetensors", + "model.layers.63.input_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.63.mlp.down_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.63.mlp.gate_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.63.mlp.up_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.k_proj.output_scale": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.k_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.o_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.q_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.v_proj.output_scale": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.63.self_attn.v_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.64.input_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.64.mlp.down_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.64.mlp.gate_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.64.mlp.up_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.k_proj.output_scale": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.k_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.o_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.q_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.v_proj.output_scale": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00047.safetensors", + "model.layers.64.self_attn.v_proj.weight_scale": "model-00024-of-00047.safetensors", + "model.layers.65.input_layernorm.weight": "model-00025-of-00047.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.65.mlp.down_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.65.mlp.gate_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.65.mlp.up_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.k_proj.output_scale": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.k_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.o_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.q_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.v_proj.output_scale": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.65.self_attn.v_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.66.input_layernorm.weight": "model-00025-of-00047.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.66.mlp.down_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.66.mlp.gate_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.66.mlp.up_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.k_proj.output_scale": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.k_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.o_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.q_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.v_proj.output_scale": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.66.self_attn.v_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.67.input_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.67.mlp.down_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.67.mlp.gate_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.67.mlp.up_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.67.self_attn.k_proj.output_scale": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.k_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.o_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.q_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.v_proj.output_scale": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00047.safetensors", + "model.layers.67.self_attn.v_proj.weight_scale": "model-00025-of-00047.safetensors", + "model.layers.68.input_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.68.mlp.down_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.68.mlp.gate_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.68.mlp.up_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.k_proj.output_scale": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.k_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.o_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.q_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.v_proj.output_scale": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.68.self_attn.v_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.69.input_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.69.mlp.down_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.69.mlp.gate_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.69.mlp.up_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.k_proj.output_scale": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.k_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.o_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.q_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.v_proj.output_scale": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.69.self_attn.v_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.7.mlp.down_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.7.mlp.gate_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.7.mlp.up_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.k_proj.output_scale": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.k_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.o_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.q_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.v_proj.output_scale": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.7.self_attn.v_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.70.input_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.70.mlp.down_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.70.mlp.gate_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.70.mlp.up_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.70.self_attn.k_proj.output_scale": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.k_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.o_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.q_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.v_proj.output_scale": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00047.safetensors", + "model.layers.70.self_attn.v_proj.weight_scale": "model-00026-of-00047.safetensors", + "model.layers.71.input_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.71.mlp.down_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.71.mlp.gate_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.71.mlp.up_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.k_proj.output_scale": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.k_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.o_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.q_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.v_proj.output_scale": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.71.self_attn.v_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.72.input_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.72.mlp.down_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.72.mlp.gate_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.72.mlp.up_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.k_proj.output_scale": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.k_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.o_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.q_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.v_proj.output_scale": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.72.self_attn.v_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.73.input_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.73.mlp.down_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.73.mlp.gate_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.73.mlp.up_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.73.self_attn.k_proj.output_scale": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.k_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.o_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.q_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.v_proj.output_scale": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00047.safetensors", + "model.layers.73.self_attn.v_proj.weight_scale": "model-00027-of-00047.safetensors", + "model.layers.74.input_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.74.mlp.down_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.74.mlp.gate_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.74.mlp.up_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.k_proj.output_scale": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.k_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.o_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.q_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.v_proj.output_scale": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.74.self_attn.v_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.75.input_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.75.mlp.down_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.75.mlp.gate_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.75.mlp.up_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.k_proj.output_scale": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.k_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.o_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.q_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.v_proj.output_scale": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.75.self_attn.v_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.76.input_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.76.mlp.down_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.76.mlp.gate_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.76.mlp.up_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.76.self_attn.k_proj.output_scale": "model-00028-of-00047.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.76.self_attn.k_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.76.self_attn.o_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.76.self_attn.q_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.76.self_attn.v_proj.output_scale": "model-00028-of-00047.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00047.safetensors", + "model.layers.76.self_attn.v_proj.weight_scale": "model-00028-of-00047.safetensors", + "model.layers.77.input_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.77.mlp.down_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.77.mlp.gate_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.77.mlp.up_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.k_proj.output_scale": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.k_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.o_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.q_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.v_proj.output_scale": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.77.self_attn.v_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.78.input_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.78.mlp.down_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.78.mlp.gate_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.78.mlp.up_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.k_proj.output_scale": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.k_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.o_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.q_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.v_proj.output_scale": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00047.safetensors", + "model.layers.78.self_attn.v_proj.weight_scale": "model-00029-of-00047.safetensors", + "model.layers.79.input_layernorm.weight": "model-00030-of-00047.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.79.mlp.down_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.79.mlp.gate_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.79.mlp.up_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.k_proj.output_scale": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.k_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.o_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.q_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.v_proj.output_scale": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.79.self_attn.v_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.8.mlp.down_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.8.mlp.gate_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.8.mlp.up_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.k_proj.output_scale": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.k_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.o_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.q_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.v_proj.output_scale": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00047.safetensors", + "model.layers.8.self_attn.v_proj.weight_scale": "model-00004-of-00047.safetensors", + "model.layers.80.input_layernorm.weight": "model-00030-of-00047.safetensors", + "model.layers.80.mlp.down_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.80.mlp.down_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.80.mlp.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.80.mlp.gate_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.80.mlp.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.80.mlp.up_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.k_proj.output_scale": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.k_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.o_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.q_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.v_proj.output_scale": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.80.self_attn.v_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.81.input_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.81.mlp.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.81.mlp.down_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.81.mlp.gate_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.81.mlp.gate_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.81.mlp.up_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.81.mlp.up_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.81.self_attn.k_proj.output_scale": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.k_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.o_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.q_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.v_proj.output_scale": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00030-of-00047.safetensors", + "model.layers.81.self_attn.v_proj.weight_scale": "model-00030-of-00047.safetensors", + "model.layers.82.input_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.82.mlp.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.82.mlp.down_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.82.mlp.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.82.mlp.gate_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.82.mlp.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.82.mlp.up_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.k_proj.output_scale": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.k_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.o_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.q_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.v_proj.output_scale": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.82.self_attn.v_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.83.input_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.83.mlp.down_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.83.mlp.down_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.83.mlp.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.83.mlp.gate_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.83.mlp.up_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.83.mlp.up_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.k_proj.output_scale": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.k_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.o_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.q_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.v_proj.output_scale": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.83.self_attn.v_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.84.input_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.84.mlp.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.84.mlp.down_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.84.mlp.gate_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.84.mlp.gate_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.84.mlp.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.84.mlp.up_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.84.self_attn.k_proj.output_scale": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.k_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.o_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.q_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.v_proj.output_scale": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00031-of-00047.safetensors", + "model.layers.84.self_attn.v_proj.weight_scale": "model-00031-of-00047.safetensors", + "model.layers.85.input_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.85.mlp.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.85.mlp.down_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.85.mlp.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.85.mlp.gate_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.85.mlp.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.85.mlp.up_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.k_proj.output_scale": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.k_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.o_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.q_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.v_proj.output_scale": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.85.self_attn.v_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.86.input_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.86.mlp.down_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.86.mlp.down_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.86.mlp.gate_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.86.mlp.gate_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.86.mlp.up_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.86.mlp.up_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.k_proj.output_scale": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.k_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.o_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.q_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.v_proj.output_scale": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.86.self_attn.v_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.87.input_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.87.mlp.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.87.mlp.down_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.87.mlp.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.87.mlp.gate_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.87.mlp.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.87.mlp.up_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.87.self_attn.k_proj.output_scale": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.k_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.o_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.q_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.v_proj.output_scale": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00032-of-00047.safetensors", + "model.layers.87.self_attn.v_proj.weight_scale": "model-00032-of-00047.safetensors", + "model.layers.88.input_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.88.mlp.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.88.mlp.down_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.88.mlp.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.88.mlp.gate_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.88.mlp.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.88.mlp.up_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.k_proj.output_scale": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.k_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.o_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.q_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.v_proj.output_scale": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.88.self_attn.v_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.89.input_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.89.mlp.down_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.89.mlp.down_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.89.mlp.gate_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.89.mlp.gate_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.89.mlp.up_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.89.mlp.up_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.k_proj.output_scale": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.k_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.o_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.q_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.v_proj.output_scale": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.89.self_attn.v_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00047.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.9.mlp.down_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.9.mlp.gate_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.9.mlp.up_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.k_proj.output_scale": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.k_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.o_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.q_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.v_proj.output_scale": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00047.safetensors", + "model.layers.9.self_attn.v_proj.weight_scale": "model-00005-of-00047.safetensors", + "model.layers.90.input_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.90.mlp.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.90.mlp.down_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.90.mlp.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.90.mlp.gate_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.90.mlp.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.90.mlp.up_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.90.self_attn.k_proj.output_scale": "model-00033-of-00047.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.90.self_attn.k_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.90.self_attn.o_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.90.self_attn.q_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.90.self_attn.v_proj.output_scale": "model-00033-of-00047.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00033-of-00047.safetensors", + "model.layers.90.self_attn.v_proj.weight_scale": "model-00033-of-00047.safetensors", + "model.layers.91.input_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.91.mlp.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.91.mlp.down_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.91.mlp.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.91.mlp.gate_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.91.mlp.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.91.mlp.up_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.k_proj.output_scale": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.k_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.o_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.q_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.v_proj.output_scale": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.91.self_attn.v_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.92.input_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.92.mlp.down_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.92.mlp.down_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.92.mlp.gate_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.92.mlp.gate_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.92.mlp.up_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.92.mlp.up_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.92.post_attention_layernorm.weight": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.k_proj.output_scale": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.k_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.k_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.o_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.o_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.q_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.q_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.v_proj.output_scale": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.v_proj.weight": "model-00034-of-00047.safetensors", + "model.layers.92.self_attn.v_proj.weight_scale": "model-00034-of-00047.safetensors", + "model.layers.93.input_layernorm.weight": "model-00035-of-00047.safetensors", + "model.layers.93.mlp.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.93.mlp.down_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.93.mlp.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.93.mlp.gate_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.93.mlp.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.93.mlp.up_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.93.post_attention_layernorm.weight": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.k_proj.output_scale": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.k_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.k_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.o_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.o_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.q_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.q_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.v_proj.output_scale": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.v_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.93.self_attn.v_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.94.input_layernorm.weight": "model-00035-of-00047.safetensors", + "model.layers.94.mlp.down_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.94.mlp.down_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.94.mlp.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.94.mlp.gate_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.94.mlp.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.94.mlp.up_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.94.post_attention_layernorm.weight": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.k_proj.output_scale": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.k_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.k_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.o_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.o_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.q_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.q_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.v_proj.output_scale": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.v_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.94.self_attn.v_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.95.input_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.95.mlp.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.95.mlp.down_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.95.mlp.gate_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.95.mlp.gate_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.95.mlp.up_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.95.mlp.up_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.95.post_attention_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.95.self_attn.k_proj.output_scale": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.k_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.k_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.o_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.o_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.q_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.q_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.v_proj.output_scale": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.v_proj.weight": "model-00035-of-00047.safetensors", + "model.layers.95.self_attn.v_proj.weight_scale": "model-00035-of-00047.safetensors", + "model.layers.96.input_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.96.mlp.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.96.mlp.down_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.96.mlp.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.96.mlp.gate_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.96.mlp.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.96.mlp.up_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.96.post_attention_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.k_proj.output_scale": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.k_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.k_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.o_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.o_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.q_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.q_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.v_proj.output_scale": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.v_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.96.self_attn.v_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.97.input_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.97.mlp.down_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.97.mlp.down_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.97.mlp.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.97.mlp.gate_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.97.mlp.up_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.97.mlp.up_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.97.post_attention_layernorm.weight": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.k_proj.output_scale": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.k_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.k_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.o_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.o_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.q_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.q_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.v_proj.output_scale": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.v_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.97.self_attn.v_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.98.input_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.98.mlp.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.98.mlp.down_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.98.mlp.gate_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.98.mlp.gate_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.98.mlp.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.98.mlp.up_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.98.post_attention_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.98.self_attn.k_proj.output_scale": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.k_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.k_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.o_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.o_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.q_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.q_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.v_proj.output_scale": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.v_proj.weight": "model-00036-of-00047.safetensors", + "model.layers.98.self_attn.v_proj.weight_scale": "model-00036-of-00047.safetensors", + "model.layers.99.input_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.99.mlp.down_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.99.mlp.down_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.99.mlp.gate_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.99.mlp.gate_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.99.mlp.up_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.99.mlp.up_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.99.post_attention_layernorm.weight": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.k_proj.output_scale": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.k_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.k_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.o_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.o_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.q_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.q_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.v_proj.output_scale": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.v_proj.weight": "model-00037-of-00047.safetensors", + "model.layers.99.self_attn.v_proj.weight_scale": "model-00037-of-00047.safetensors", + "model.norm.weight": "model-00046-of-00047.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b15bd5bede8646b778d6fe13a84bc1eebe5ccb6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18094ff23c44609d705eb254f44ae1d922906628ef13ac72ce2d617946ecb09e +size 17210182 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3e3784073f3c038cb5cba05e14bcb9bad576a9a2 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 512, + "pad_token": "<|eot_id|>", + "padding_side": "left", + "tokenizer_class": "PreTrainedTokenizer" +}