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/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..523e529c053f058aae77af66d4a0dd9c5b831a61 --- /dev/null +++ b/README.md @@ -0,0 +1,44 @@ +--- +language: +- en +- zh +library_name: transformers +license: mit +pipeline_tag: text-generation +base_model: zai-org/GLM-4.6 +tags: +- mlx +--- + +# cs2764/GLM-4.6-mlx-6Bit + +The Model [cs2764/GLM-4.6-mlx-6Bit](https://huggingface.co/cs2764/GLM-4.6-mlx-6Bit) was converted to MLX format from [zai-org/GLM-4.6](https://huggingface.co/zai-org/GLM-4.6) using mlx-lm version **0.28.0**. + +## Quantization Details + +This model was converted with the following quantization settings: + +- **Quantization Strategy**: 6-bit quantization +- **Average bits per weight**: 6.502 + +## Use with mlx + +```bash +pip install mlx-lm +``` + +```python +from mlx_lm import load, generate + +model, tokenizer = load("cs2764/GLM-4.6-mlx-6Bit") + +prompt="hello" + +if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: + messages = [{"role": "user", "content": prompt}] + prompt = tokenizer.apply_chat_template( + messages, tokenize=False, add_generation_prompt=True + ) + +response = generate(model, tokenizer, prompt=prompt, verbose=True) +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..41478957aca7a04b7321022e7d1f73de5badd995 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{{ visible_text(m.content) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson(ensure_ascii=False) if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '\n' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4deb71e07197d85dca751135bbdf2a96cffcd3be --- /dev/null +++ b/config.json @@ -0,0 +1,53 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 3, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 202752, + "model_type": "glm4_moe", + "moe_intermediate_size": 1536, + "n_group": 1, + "n_routed_experts": 160, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 92, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "quantization": { + "group_size": 64, + "bits": 6, + "mode": "affine" + }, + "quantization_config": { + "group_size": 64, + "bits": 6, + "mode": "affine" + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 2.5, + "tie_word_embeddings": false, + "topk_group": 1, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.0", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f51194759eb31dde6fbc75a28e3fb7036f68161a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "temperature": 1.0, + "transformers_version": "4.56.2" +} diff --git a/model-00001-of-00054.safetensors b/model-00001-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0ddc80b9fb34efc8067db237cfb9d228c3cfb797 --- /dev/null +++ b/model-00001-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651de89c10bbc509155b13df3f0b9c4e1974376e367e3eee1dec9267c118ee7f +size 4732435585 diff --git a/model-00002-of-00054.safetensors b/model-00002-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..09dd8cdbcd7d2f76506b8110c41739817a9abe20 --- /dev/null +++ b/model-00002-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663969396a528243b56d9ca5f5308fa480d973b680badc4298af23a95a144803 +size 5243427265 diff --git a/model-00003-of-00054.safetensors b/model-00003-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60f95194e6821b1b381737aa474e2fa529d57294 --- /dev/null +++ b/model-00003-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5294979e3f3e3be0bf7ced5f83ff2a9ecd44f64014b1aa2f8f727139f9094727 +size 5335722898 diff --git a/model-00004-of-00054.safetensors b/model-00004-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..70e006f599c82f45b5cd2a1dabbd036ac67807fc --- /dev/null +++ b/model-00004-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c1b13cddbc08cbb94651b25e076b9565d53dd46e743651bc2b3ce8553680c8 +size 5363247106 diff --git a/model-00005-of-00054.safetensors b/model-00005-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1c8bfa8fc28de5fc5053f39eb2e4ac3a7c0c6e6 --- /dev/null +++ b/model-00005-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fcb3e6fef5f12a7062ae2694154645a55d1313c1582ece752656e532121fb3e +size 5294546458 diff --git a/model-00006-of-00054.safetensors b/model-00006-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c2145c91479b11e474fe29336d0232c6d9625c8 --- /dev/null +++ b/model-00006-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c006861df314f0d5c03cee80d62d0b22c4c0c509747a9a4b2c75de0f7ec8a772 +size 5335722946 diff --git a/model-00007-of-00054.safetensors b/model-00007-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a34271b0c6fd18a0d29f3eeeee13f4ecaf70f798 --- /dev/null +++ b/model-00007-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554ca4ebb1d0057f528b4f5814165894da24fe7a256565dca5e51bd8148a7640 +size 5363247185 diff --git a/model-00008-of-00054.safetensors b/model-00008-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1561bf5d05070d0aa863060479abf3d8b45ac423 --- /dev/null +++ b/model-00008-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43fdfb0f384f6c46ac5a25ca06ac717eed7b6cab28cef40e890c7a4540222a7 +size 5294546451 diff --git a/model-00009-of-00054.safetensors b/model-00009-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ffaf8e240409669bfee0eaf930eb842022c026f --- /dev/null +++ b/model-00009-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610bd0de3537e203ce02c19c76691eaf5f2f7ac76cae7c7681a20cd6dc3ac84c +size 5335722966 diff --git a/model-00010-of-00054.safetensors b/model-00010-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5be85137f7d12d7c7582f059cbb80a6207f0f6c --- /dev/null +++ b/model-00010-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e653dbd679a7471a3b8e86e5ba49f981ad7bc7e007d3fa40d051e431707938d +size 5363247163 diff --git a/model-00011-of-00054.safetensors b/model-00011-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc0e05f410c2b44df8111e04348a98c1cd8f1b81 --- /dev/null +++ b/model-00011-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdad75f6c388efe0106b30d17ae087d62b9edae24b22e0e8dcd457065f3b3eca +size 5294546461 diff --git a/model-00012-of-00054.safetensors b/model-00012-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e155d3718109f2228270f082735fa8d920052dfa --- /dev/null +++ b/model-00012-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b3e0a6ce477c58b8717e96cade9485d59606b7075f0c5231541941c9ee9906 +size 5335722940 diff --git a/model-00013-of-00054.safetensors b/model-00013-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..360467790f19ae0e085ec34de371f1ac76b56c5d --- /dev/null +++ b/model-00013-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f3301fc2d137d1303a5d57e544959ecc4f7f0a1f72e4e91fcb8d78f1f6a9695 +size 5363247197 diff --git a/model-00014-of-00054.safetensors b/model-00014-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b808c3431436fc3bc7d9a58786718da6dc8e39ac --- /dev/null +++ b/model-00014-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f60aadb4160f8f9490872aa70c422ebac940d1c1130a3aa693481851bd47183 +size 5294546487 diff --git a/model-00015-of-00054.safetensors b/model-00015-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20674419fb3d26f957aa345645e2e7ad6fe7d9d8 --- /dev/null +++ b/model-00015-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3863fead247704010f027c2945e77c193c24f353bc3ff1a9ffa8c16c09ef4a53 +size 5335722976 diff --git a/model-00016-of-00054.safetensors b/model-00016-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae28ef755d65d013d2149424796ba8438d0a2e6b --- /dev/null +++ b/model-00016-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c7abcebb3cc21dd3176418d36ad10f64f3404dca21ae1a43fdde542448a4e9 +size 5363247143 diff --git a/model-00017-of-00054.safetensors b/model-00017-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77af7df02cdc45d70cc1b4aac2fb7e62a98d6c03 --- /dev/null +++ b/model-00017-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00246155e177e0be2afcbcda99d56e89b8e601a77ea05eb5bf18bff66a85a5b +size 5294546487 diff --git a/model-00018-of-00054.safetensors b/model-00018-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8e47173358f0619a528806c4ba6e676087abb46 --- /dev/null +++ b/model-00018-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35bcc543c57a17e1f57b5e68cdb5036aad970580ba0367f96eb5ed7bc709e028 +size 5335722962 diff --git a/model-00019-of-00054.safetensors b/model-00019-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..423574fa4a73f361d08edc3f7facbb11a9c22682 --- /dev/null +++ b/model-00019-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9e3cf786ccf08795d453dff901a1a74771f9283009bf63f1a34d7654bb8e1d +size 5363247181 diff --git a/model-00020-of-00054.safetensors b/model-00020-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05d0845855d519215d25a6e12d8dc9bb486342d9 --- /dev/null +++ b/model-00020-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7223cc2f3abe72b3bf3da7e76577d30b5dfb2203c1f46ab2389064eed8a6f152 +size 5294546489 diff --git a/model-00021-of-00054.safetensors b/model-00021-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fedfe583b8c9399ef27d4923aeb560444e676c51 --- /dev/null +++ b/model-00021-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a0a63141efd0a6b4118612dc633f810abac22e3d0d8efdd0cf71a8722ceede +size 5335722984 diff --git a/model-00022-of-00054.safetensors b/model-00022-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2df0c63baeae2f15f5eec245f4fd7a1a51da1e09 --- /dev/null +++ b/model-00022-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3a295840275c5b0cf0071d2184985e742ed40eaa7d7c119254636658d8f016 +size 5363247173 diff --git a/model-00023-of-00054.safetensors b/model-00023-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd48b1d3cb2886fc448186e1679cd418c3d8d413 --- /dev/null +++ b/model-00023-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364864110ee87ebe121cf13d61cb2a6a372eaf547e49af12c7d4b7d26dc45ddc +size 5294546481 diff --git a/model-00024-of-00054.safetensors b/model-00024-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c375d8869251b2dd1df103cd2c344eb6658986af --- /dev/null +++ b/model-00024-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58c3d73ed5dff2df23c2e92f52c83c26a6c17c3afbe4dc9f283098f8b4b7207 +size 5335722908 diff --git a/model-00025-of-00054.safetensors b/model-00025-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b890cf8f8580c670d9a9a19cc470473c5d581f43 --- /dev/null +++ b/model-00025-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6e495fb5a80895cb8b81b7560b39b94a6c38752d18cb52c1d80afb421634e47 +size 5363247193 diff --git a/model-00026-of-00054.safetensors b/model-00026-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a1e4fa8775cb7493aae3b8c2e4e7ffaaa3ce4db --- /dev/null +++ b/model-00026-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa654f20c7168b9c2f50b4e039f9f069ff7b73511620ecc6f244dcfe560ab4e3 +size 5294546487 diff --git a/model-00027-of-00054.safetensors b/model-00027-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e46705e158e252eaa825fc403f99961a794fb341 --- /dev/null +++ b/model-00027-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02489e05d453416bacdb5a9ec258ed49dfc6d7e846acffd5d22a8d533676b358 +size 5335722916 diff --git a/model-00028-of-00054.safetensors b/model-00028-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58966088341ef5d9a1a920e320db83146028cf02 --- /dev/null +++ b/model-00028-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc12fbcb7ba1a6239acbeac737488b801957a9a0509106e8be2f45a415cbf95 +size 5363247169 diff --git a/model-00029-of-00054.safetensors b/model-00029-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fa24a5c0ed7c6437edabd880ac060ca30e1d715c --- /dev/null +++ b/model-00029-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d54fa57b37bd685ebf4c3d5724ad184b401688b2c803dd67594d5618164a47 +size 5294546487 diff --git a/model-00030-of-00054.safetensors b/model-00030-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51e227cce2ff41b901afabd54db60907e5800b51 --- /dev/null +++ b/model-00030-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70f38843c83f55b4ce516ee2a2c490917dde226143c3ff421f6b3e153c6f532 +size 5335722970 diff --git a/model-00031-of-00054.safetensors b/model-00031-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28ac8505a2a52cb580ab5a9220eae1b0d5da5e3f --- /dev/null +++ b/model-00031-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266742861fdceb9f54d46810c5c0fc5d60c230989ad74e7323f70f78536de6d7 +size 5363247195 diff --git a/model-00032-of-00054.safetensors b/model-00032-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13393f9a04dd3253fc6ccd64365bfa82ff009586 --- /dev/null +++ b/model-00032-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d93c98569bbfb4dd8c1af9f4d283adfd5c139bff3c88a4bfebffd48cb928528 +size 5294546489 diff --git a/model-00033-of-00054.safetensors b/model-00033-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5313c933513515a0381f8e5a624c206e17854065 --- /dev/null +++ b/model-00033-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9a3738cd42ce5f03b1624ab100f870a2af04870a4c90b96d08367e4c7a46b4a +size 5335722968 diff --git a/model-00034-of-00054.safetensors b/model-00034-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6a65d699486ce172cbcd2a20dfa2162bfe089ea --- /dev/null +++ b/model-00034-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6acd6c99b4d2c25c1b7e109b26309e6b5fc83fc6e266ad27a719fdd505825fa7 +size 5363247173 diff --git a/model-00035-of-00054.safetensors b/model-00035-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21a43895869c434ae63412991ffc20259dc47cae --- /dev/null +++ b/model-00035-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929febcaa26abe331aa4d1e3aaf0e636781486d25efb870a1bd253a39a45df15 +size 5294546489 diff --git a/model-00036-of-00054.safetensors b/model-00036-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8856498d0073d71d76472122907ec8b8aaae1f2 --- /dev/null +++ b/model-00036-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946a521f24b5489b0c21c204228a9940139c08792c73406c64d59c85f81f0b98 +size 5335722910 diff --git a/model-00037-of-00054.safetensors b/model-00037-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5c1a430a5d876b5f8444b06120fdb85e0becf17 --- /dev/null +++ b/model-00037-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0a07f2340f8a2644f9871fd85ddb2914de56bd703a7c4f336cc1ea983dbb11 +size 5363247177 diff --git a/model-00038-of-00054.safetensors b/model-00038-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0797de64bd4961059df1a4b70b0533bc6b480d8 --- /dev/null +++ b/model-00038-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9aaa71c0e3011ee5e1153774ff71208f475bbde3f79839fae073fbbd54ebe9 +size 5294546491 diff --git a/model-00039-of-00054.safetensors b/model-00039-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e858dbe728a6205aaac4190305f27d51296a79b8 --- /dev/null +++ b/model-00039-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de76a40b1738565371c056365305dd04f654923d13a9912adcdece0f3fa83e0e +size 5335722982 diff --git a/model-00040-of-00054.safetensors b/model-00040-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9eab4684d974b723c98001061470beda692d10d6 --- /dev/null +++ b/model-00040-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7b631b903d630b79f73ccb2d764a7830a8969f5ccb768711f826a6ceb12ea8 +size 5363247177 diff --git a/model-00041-of-00054.safetensors b/model-00041-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8aa5bc708c9a542d1429579e6892c510c37cc378 --- /dev/null +++ b/model-00041-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55322ea59aef6410b27807253ad611732e369d2f90f322aeda8db66ecbb8cbf8 +size 5294546479 diff --git a/model-00042-of-00054.safetensors b/model-00042-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..156e581fba13854ed9a05b14f2c2b1047b9f6ba3 --- /dev/null +++ b/model-00042-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2271b2cb7dc4f8e26df910d1ff06b0187853861b6bbd8e2c8ea536a91aa8533 +size 5335722966 diff --git a/model-00043-of-00054.safetensors b/model-00043-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c06b042c46a6f1215e1bd773fbcd6a5e4282d6e --- /dev/null +++ b/model-00043-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28997f45c43ec45f34b30c8c1e41a0a7e5547500be9a6e9d55a31bbcd4b5fec +size 5363247181 diff --git a/model-00044-of-00054.safetensors b/model-00044-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07c14bc173660c06cba2ef5e72050941c9841e98 --- /dev/null +++ b/model-00044-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353d1aab366d8693a214d9a7380c0f30d5b8d73df3cc0ad9df7dd3cc2a004138 +size 5294546447 diff --git a/model-00045-of-00054.safetensors b/model-00045-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e04fb27f09eb79fbd528e197aefbb3985deef121 --- /dev/null +++ b/model-00045-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd4c5e00e11a4804b7aeffe52bf3b6d51ad1ab4df44ca951c7fff06624876f1 +size 5335722978 diff --git a/model-00046-of-00054.safetensors b/model-00046-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b243f4949189b3011e318f6c6144f72990f20ae --- /dev/null +++ b/model-00046-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344ef896e465efc615c1d8f8781b7c493101af3443520f76d0a9d06365c29e94 +size 5363247189 diff --git a/model-00047-of-00054.safetensors b/model-00047-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3252a3986ddd4a1747d5e22e1aed1c48e5fd7a9 --- /dev/null +++ b/model-00047-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ebde2a1f984e89b80c1185dae37d406b0865fa13917920b80021cff9e7a0f1 +size 5294546487 diff --git a/model-00048-of-00054.safetensors b/model-00048-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b39dde640b2b0d0ee4bdadb5fb4ba852baada82 --- /dev/null +++ b/model-00048-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e97c07eba6d7943c278e0aee8cbb9ac3a58217ded7a3b26a5998570cf3eb7b +size 5335722980 diff --git a/model-00049-of-00054.safetensors b/model-00049-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7d2510f8789b77f8e5bd9b6fae437c1f976ee58 --- /dev/null +++ b/model-00049-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636b90c616bb517f5e76ae79b032728eb4ba33ac14a4887d19efc41ab7642ee3 +size 5363247191 diff --git a/model-00050-of-00054.safetensors b/model-00050-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a96606a6fade22843a08fdd90256e0fac975d9c --- /dev/null +++ b/model-00050-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fce88f7cc84919910b469234035babd49f64cedf971610eafd1c52278e24f3d +size 5294546489 diff --git a/model-00051-of-00054.safetensors b/model-00051-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e93366893f1238faadac2f06fcdb1cac4d411ca --- /dev/null +++ b/model-00051-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf42c9121a2cca4a14e0dfd2be47d99381d6a876cf073a47d233e0009fb5082 +size 5335722964 diff --git a/model-00052-of-00054.safetensors b/model-00052-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a917e592f247fa9141d977230191e07a5fbe1888 --- /dev/null +++ b/model-00052-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610709894676e3c2caa146d799f7d673eeae6d107fc10efa2ca719e52536b6f4 +size 5363247191 diff --git a/model-00053-of-00054.safetensors b/model-00053-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2b1b28fdd3b33f6691475edebd8a9eea41722e8 --- /dev/null +++ b/model-00053-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f50dd879a876637344ceb9d9de21c8e3aeba88ee4eaa34497a876167bfccee +size 5294546487 diff --git a/model-00054-of-00054.safetensors b/model-00054-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..348a96a5b0d2212858a8b535a1f3e5ebe4fd7fb5 --- /dev/null +++ b/model-00054-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60d9da765d46d13e8d7eaa81e84d442e4587713a74745eec0433fd7d4bcc8d7 +size 4872362644 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e3c83201499eb9ea25e90dfe2fb1df03a8860d38 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3570 @@ +{ + "metadata": { + "total_size": 286737579648, + "total_parameters": 352797829024 + }, + "weight_map": { + "lm_head.biases": "model-00054-of-00054.safetensors", + "lm_head.scales": "model-00054-of-00054.safetensors", + "lm_head.weight": "model-00054-of-00054.safetensors", + "model.embed_tokens.biases": "model-00001-of-00054.safetensors", + "model.embed_tokens.scales": "model-00001-of-00054.safetensors", + "model.embed_tokens.weight": "model-00001-of-00054.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.10.input_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.gate.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.o_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.11.input_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.gate.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.o_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.input_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.gate.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.o_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.13.input_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.gate.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.o_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.14.input_layernorm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.gate.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.o_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.15.input_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.gate.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.o_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.16.input_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.gate.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.o_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.input_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.gate.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.o_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.18.input_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.gate.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.o_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.19.input_layernorm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.gate.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.o_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.20.input_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.gate.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.o_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.21.input_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.gate.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.o_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.input_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.gate.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.o_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.23.input_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.gate.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.o_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.24.input_layernorm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.gate.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.o_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.25.input_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.gate.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.o_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.26.input_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.gate.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.o_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.input_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.gate.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.o_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.28.input_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.gate.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.o_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.29.input_layernorm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.gate.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.o_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.gate.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.30.input_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.gate.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.o_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.31.input_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.gate.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.o_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.input_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.gate.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.o_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.33.input_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.gate.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.o_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.34.input_layernorm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.gate.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.o_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.35.input_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.gate.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.o_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.36.input_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.gate.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.o_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.input_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.gate.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.o_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.38.input_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.gate.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.o_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.39.input_layernorm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.gate.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.o_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.gate.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00054.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.40.input_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.gate.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.o_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.41.input_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.gate.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.o_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.input_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.gate.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.o_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.43.input_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.gate.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.o_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.44.input_layernorm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.gate.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.o_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.45.input_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.gate.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.o_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.46.input_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.gate.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.o_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.input_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.gate.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.o_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.48.input_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.gate.e_score_correction_bias": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.gate.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.o_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.49.input_layernorm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.gate.e_score_correction_bias": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.gate.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.o_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.gate.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.o_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.50.input_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.gate.e_score_correction_bias": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.gate.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.o_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.51.input_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.gate.e_score_correction_bias": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.gate.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.o_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.input_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.gate.e_score_correction_bias": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.gate.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.o_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.53.input_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.gate.e_score_correction_bias": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.gate.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.o_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.54.input_layernorm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.gate.e_score_correction_bias": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.gate.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.o_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.55.input_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.gate.e_score_correction_bias": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.gate.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.o_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.56.input_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.gate.e_score_correction_bias": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.gate.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.o_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.input_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.gate.e_score_correction_bias": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.gate.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.o_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.58.input_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.gate.e_score_correction_bias": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.gate.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.o_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.59.input_layernorm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.gate.e_score_correction_bias": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.gate.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.o_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.gate.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.o_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.60.input_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.gate.e_score_correction_bias": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.gate.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.o_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.o_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.61.input_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.gate.e_score_correction_bias": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.gate.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.o_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.o_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.input_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.gate.e_score_correction_bias": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.gate.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.o_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.o_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.63.input_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.gate.e_score_correction_bias": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.gate.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.o_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.o_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.64.input_layernorm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.gate.e_score_correction_bias": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.gate.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.k_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.o_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.o_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.q_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.65.input_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.gate.e_score_correction_bias": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.gate.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.65.self_attn.k_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.bias": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.o_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.o_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.bias": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.bias": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.66.input_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.gate.e_score_correction_bias": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.gate.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.o_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.o_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.input_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.gate.e_score_correction_bias": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.gate.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.67.self_attn.k_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.o_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.o_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.68.input_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.gate.e_score_correction_bias": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.gate.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_norm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.o_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.o_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_norm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.69.input_layernorm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.gate.e_score_correction_bias": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.gate.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.k_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.o_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.o_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.q_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.gate.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.o_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.70.input_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.gate.e_score_correction_bias": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.gate.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.70.self_attn.k_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.bias": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.o_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.o_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.bias": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.bias": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.71.input_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.gate.e_score_correction_bias": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.gate.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.o_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.o_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.input_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.gate.e_score_correction_bias": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.gate.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.72.self_attn.k_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.o_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.o_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.73.input_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.gate.e_score_correction_bias": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.gate.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_norm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.o_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.o_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_norm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.74.input_layernorm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.gate.e_score_correction_bias": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.gate.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.k_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.o_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.o_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.q_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.75.input_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.gate.e_score_correction_bias": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.gate.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.75.self_attn.k_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.bias": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.o_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.o_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.bias": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.bias": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.76.input_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.gate.e_score_correction_bias": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.gate.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.o_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.o_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.input_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.gate.e_score_correction_bias": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.gate.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.77.self_attn.k_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.o_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.o_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.78.input_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.gate.e_score_correction_bias": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.gate.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_norm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.o_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.o_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_norm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.79.input_layernorm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.gate.e_score_correction_bias": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.gate.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.k_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.o_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.o_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.q_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.gate.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.o_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.80.input_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.gate.e_score_correction_bias": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.gate.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.80.self_attn.k_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.bias": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.o_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.o_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.bias": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.bias": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.81.input_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.gate.e_score_correction_bias": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.gate.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.o_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.o_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.input_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.gate.e_score_correction_bias": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.gate.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.82.self_attn.k_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.o_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.o_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.83.input_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.gate.e_score_correction_bias": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.gate.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_norm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.o_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.o_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_norm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.84.input_layernorm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.gate.e_score_correction_bias": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.gate.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.k_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.o_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.o_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.q_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.85.input_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.gate.e_score_correction_bias": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.gate.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.85.self_attn.k_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.bias": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.o_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.o_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.bias": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.bias": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.86.input_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.gate.e_score_correction_bias": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.gate.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.o_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.o_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.input_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.gate.e_score_correction_bias": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.gate.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.87.self_attn.k_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.o_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.o_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.88.input_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.gate.e_score_correction_bias": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.gate.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_norm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.o_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.o_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_norm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.89.input_layernorm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.gate.e_score_correction_bias": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.gate.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.k_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.o_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.o_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.q_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.gate.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.o_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.90.input_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.gate.e_score_correction_bias": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.gate.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.90.self_attn.k_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.bias": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.o_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.o_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.bias": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.bias": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.91.input_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.gate.e_score_correction_bias": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.gate.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_norm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.bias": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.o_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.o_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_norm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.bias": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.bias": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00054-of-00054.safetensors", + "model.norm.weight": "model-00054-of-00054.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..9028cf84013844f17d7616bdec1d88e977924434 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,40 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ed3c66baf1ec4de61840b0abf02142687bfed8 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba +size 19970700 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..053f12c9b03d5acbcc921042ea0c87a6baa5d3f7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,325 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizer" +}