diff --git a/.cache/._huggingface b/.cache/._huggingface new file mode 100644 index 0000000000000000000000000000000000000000..252be49e579e89990bb6e29900bd105e5bd1c12e Binary files /dev/null and b/.cache/._huggingface differ 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..91e03fa6f3ba5422b3a2799549c4342e49893887 --- /dev/null +++ b/README.md @@ -0,0 +1,54 @@ +--- +license: mit +base_model: Ex0bit/GLM-4.7-PRISM +model_name: Elbaz-GLM-4.7-PRISM +tags: +- abliteration +- SOTA Abliteration Pipeline - PRISM +- glm +- glm4_moe +- quantized +- finetuned +- uncensored +- abliterated +- mlx +- mlx-my-repo +language: +- en +- zh +library_name: transformers +pipeline_tag: text-generation +--- + +# cs2764/GLM-4.7-PRISM-mlx-6Bit + +The Model [cs2764/GLM-4.7-PRISM-mlx-6Bit](https://huggingface.co/cs2764/GLM-4.7-PRISM-mlx-6Bit) was converted to MLX format from [Ex0bit/GLM-4.7-PRISM](https://huggingface.co/Ex0bit/GLM-4.7-PRISM) using mlx-lm version **0.30.4**. + +## 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-4.7-PRISM-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..2ab98ef068d62829d17c5ade1827b9f013fa2bbf --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,86 @@ +[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) }} +{%- 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 ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%} +{{ '' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '' }} +{%- endif -%} +{%- if content.strip() -%} +{{ content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{- '' + 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 %} +{{- '' }} +{{- m.content }} +{{- '' }} +{%- 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|>{{- '' 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..81693ac0de45c725aa09edc877333ff377a46630 --- /dev/null +++ b/config.json @@ -0,0 +1,53 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "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": 0, + "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, + "transformers_version": "4.57.3", + "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..a7958b7d81d1338ae40db2fd0d9d030effc9e41d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "transformers_version": "4.57.3" +} diff --git a/model-00001-of-00054.safetensors b/model-00001-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8bcce498cedf41a18e9e97d82d53bf800947a83 --- /dev/null +++ b/model-00001-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba03c8a696633fd4b15610301ca83f214f930342b5fbd843e58bdc1799588417 +size 4732435585 diff --git a/model-00002-of-00054.safetensors b/model-00002-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8b06216184948a2579c6fc39031559471c63a86 --- /dev/null +++ b/model-00002-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9c2fa6c5d257126a37383a064377a0e1f57f7305e591fd57e629ec083d4b01 +size 5243427265 diff --git a/model-00003-of-00054.safetensors b/model-00003-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68422437ba98d6b16a701d18618f3a7b35a25d40 --- /dev/null +++ b/model-00003-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b8877c40d1096ba08ea5005f1f0231513e4a563ff1f2609bd5763a0e93b2df +size 5335722898 diff --git a/model-00004-of-00054.safetensors b/model-00004-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3dcb8dbde57f6dc9df222b8f1ca9f0670aa195a --- /dev/null +++ b/model-00004-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1371cd56d328eff13f2707f972d1df54f5f7e2ec885512084e39c3710e5c10ca +size 5363247106 diff --git a/model-00005-of-00054.safetensors b/model-00005-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07c4262ee2343acf0adcc026272b5370143633d5 --- /dev/null +++ b/model-00005-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072382f332932e469187b15d5936d4bd766ffb0181e333a71c663d3e4628c534 +size 5294546458 diff --git a/model-00006-of-00054.safetensors b/model-00006-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6073ee633576336cd1ad052018c2f1bcc6a801d7 --- /dev/null +++ b/model-00006-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301065e97eb8d631a71efaac807d57170c8e17dfd93a222a31be676ea7c6ffc5 +size 5335722946 diff --git a/model-00007-of-00054.safetensors b/model-00007-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a467e7688285ab1e6a3cc794d272b9fbc89da506 --- /dev/null +++ b/model-00007-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc0a5b9b68b89ae04f25d6536be60d67aaf4e7379b969154bf5e31d4910910a5 +size 5363247185 diff --git a/model-00008-of-00054.safetensors b/model-00008-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e01e966396d49dfce7c4ee8874ee0a7c25cee5a3 --- /dev/null +++ b/model-00008-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa362e004a657ffb5ab58289299164b4300e9cc69d0aaf5a2033930279b9b008 +size 5294546451 diff --git a/model-00009-of-00054.safetensors b/model-00009-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..219cadc8e530ab640c2147c3b88326ce52fc5948 --- /dev/null +++ b/model-00009-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06844ca57df6c056a5b9eb2a50baff4ae4aebe47209c69a102b53a2cf811040f +size 5335722966 diff --git a/model-00010-of-00054.safetensors b/model-00010-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b6226a7271f7d58e03e53a888064cdefde1898a --- /dev/null +++ b/model-00010-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007317079e2fd9949408d7fbc04dfdba69622cd7a6d49484eb3090e6fe191979 +size 5363247163 diff --git a/model-00011-of-00054.safetensors b/model-00011-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2e5f2691f05830eaa57f3dac290d8a013f21bf2 --- /dev/null +++ b/model-00011-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5007f6ea7b13c3a34b2791bb0e35f5a13875c2524b3af0d31b56aa0fe6ffc2a8 +size 5294546461 diff --git a/model-00012-of-00054.safetensors b/model-00012-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a859e405da5fa1a293aad828e2246a12edb3d7c8 --- /dev/null +++ b/model-00012-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd3ae73a6a34a1bceec05db962eb0c9a75a30503df5b7af75586d779fb0f062 +size 5335722940 diff --git a/model-00013-of-00054.safetensors b/model-00013-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8f587a7eb28584dad5789bc159f66ea40c75fed --- /dev/null +++ b/model-00013-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0c748e94eb5795265efedf132fe9bb89ed3ed5f7bb4e0fc2a405e817c2f6b1 +size 5363247197 diff --git a/model-00014-of-00054.safetensors b/model-00014-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26f14805c4069a3a1c825608ef430ac3a6476f57 --- /dev/null +++ b/model-00014-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2a43ba7d7d889755899949a2c8ffe7ede719ca1d51d400ade6bed6f0394720 +size 5294546487 diff --git a/model-00015-of-00054.safetensors b/model-00015-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7791d0ed614e64d44ee46f01d7503fd5b8c19c69 --- /dev/null +++ b/model-00015-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eec7c372c489c3bc74d96ffd444fc671680b4b8e4997d0dd4fd1ded0dbc3a58 +size 5335722976 diff --git a/model-00016-of-00054.safetensors b/model-00016-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..499f0b4c208bd95365809c18748a40d0e4878e86 --- /dev/null +++ b/model-00016-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988921c93f8bf5c93748db558e2fdf4e9d50d9d7a06fd0cb8768c48c27c73ac5 +size 5363247143 diff --git a/model-00017-of-00054.safetensors b/model-00017-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..331bea88a74cce7d42857e58328aed2115616b1c --- /dev/null +++ b/model-00017-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7f6d115633658f7079bf13ad4ae7ea2c297c9af990b87ff61136ff9f7189c5 +size 5294546487 diff --git a/model-00018-of-00054.safetensors b/model-00018-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d20cc6dbf5929794fc963b07d1913106ed9e6617 --- /dev/null +++ b/model-00018-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626461cdc99102326bc652beec02b9c98b096dc514a915d9114f475eeca6b7c7 +size 5335722962 diff --git a/model-00019-of-00054.safetensors b/model-00019-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..383d55dd16b0db7ed815dc421e9a27155b6f4d95 --- /dev/null +++ b/model-00019-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0698449f1212f8aa85e9652b5cf1e3937f57213ec16894a771d4a3ffecbc866a +size 5363247181 diff --git a/model-00020-of-00054.safetensors b/model-00020-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd445eda84a3f0767a20c13761a4f21ac8a43d07 --- /dev/null +++ b/model-00020-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19a9603d53bbe923224ed0f449be3d8885c1541426c59e2e44b08af25b3c0cb +size 5294546489 diff --git a/model-00021-of-00054.safetensors b/model-00021-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3bb00edbd2813c0b86e18b9fc65e0b5fc72ac1b3 --- /dev/null +++ b/model-00021-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153754f5f9166d3c60531b9f7171c00b7632e319e9dcaef6a317273831b69d8c +size 5335722984 diff --git a/model-00023-of-00054.safetensors b/model-00023-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1dcd588718f64059fee9aceeff02bfc5e16d635e --- /dev/null +++ b/model-00023-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17bee436570b426c7ea2cb49737837759e1c09206a7f0d290be5ef3253b49494 +size 5294546481 diff --git a/model-00024-of-00054.safetensors b/model-00024-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..81302eb62b4d703008eecbedee29c45f889c318d --- /dev/null +++ b/model-00024-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e387da82f550c85299a3c0c88ed06dbbc91a929f1dce991e4fc0035ea0695e46 +size 5335722908 diff --git a/model-00026-of-00054.safetensors b/model-00026-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d1fa85c2d1463e74492b7f8d310101fd717944f --- /dev/null +++ b/model-00026-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdff223a82658b5544e063aeb91ec2d857e725e16179c04841c133ada833676d +size 5294546487 diff --git a/model-00029-of-00054.safetensors b/model-00029-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9d4b63fe8cb7a52d9e81643f38f87d5f1beb9fa --- /dev/null +++ b/model-00029-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c771d3a763e3a1b3ba294179a8cba8df7f457e1cc63fc63a00f7b86a341521d0 +size 5294546487 diff --git a/model-00037-of-00054.safetensors b/model-00037-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3dbc6940f5b2ecfef884d8de0e43c593dc59edbc --- /dev/null +++ b/model-00037-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c255aa91124eee1e192b5d31d789a031388d9dd125290f7c5af9c198874611 +size 5363247177 diff --git a/model-00039-of-00054.safetensors b/model-00039-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d918ac3cf20a3179ae405e5aff00937ce7a72bb --- /dev/null +++ b/model-00039-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b15b0aed51b6367be653dfcd109d60e7227372cb9e9ce580626523939d7d4a1 +size 5335722982 diff --git a/model-00040-of-00054.safetensors b/model-00040-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b605d09fcc29dfb46b28f76af3fc8697ba3269c7 --- /dev/null +++ b/model-00040-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c937c7987b82cc1dd2ba6f8cc37801affb3bcdcfbcc6e4a56bddcd862735b0 +size 5363247177 diff --git a/model-00041-of-00054.safetensors b/model-00041-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a236850536f95f10de11aab0a24cf4bdbe83da94 --- /dev/null +++ b/model-00041-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62aecc560041dfdfc3c06c9d5ff07cdb1fe5ab220921f4349038e07c78d0211e +size 5294546479 diff --git a/model-00042-of-00054.safetensors b/model-00042-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2dedd6359545034d10c9fc3219d914fdd83e2b74 --- /dev/null +++ b/model-00042-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ecdc56c9cde9f0985640d09dbe9507542ac6df3dd31ccbab66f8b02b19b3cb +size 5335722966 diff --git a/model-00043-of-00054.safetensors b/model-00043-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..520e7330e69d91a88061cbf50c6aef936892c56e --- /dev/null +++ b/model-00043-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb7269a795cf6e87132c7ea54022c9d6909d8efbec050bafa37b99d77f3d1e7 +size 5363247181 diff --git a/model-00044-of-00054.safetensors b/model-00044-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b88a51a87abd4bbee0867258516d9b87aa0bb5e --- /dev/null +++ b/model-00044-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec8372b5baa4f4bce9fa268386e2bfe794c5184d9e6af9c0327d59f1b92f97f +size 5294546447 diff --git a/model-00045-of-00054.safetensors b/model-00045-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dbf6696bdf3608878c1ff6afe1a98ce83c7f60d8 --- /dev/null +++ b/model-00045-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662e54b6b82fed986c215b8d4fb1dc7751941d4d00f8a68c71cf500ab966ee3a +size 5335722978 diff --git a/model-00046-of-00054.safetensors b/model-00046-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24056ef2fbb348a46ca947497fefcd64d8703649 --- /dev/null +++ b/model-00046-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da5fb1257fcb73dd8be77a8f7e01484cbf5f4ef93ed5cdb55fc8a16a8a6dfb7 +size 5363247189 diff --git a/model-00047-of-00054.safetensors b/model-00047-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..928904068f2eb6bf49f71d37fbe1fac5d5b67558 --- /dev/null +++ b/model-00047-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735a7b36c85a542d3c7b435beecff5a0dc1f869a5273e326dcbe1b4143e96edc +size 5294546487 diff --git a/model-00048-of-00054.safetensors b/model-00048-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d40ae15231c1eb7370304d3027c3d2799d3d836c --- /dev/null +++ b/model-00048-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e75d8f1b1cad7a097daeb66872c4174db1f059c9d0da9cc009c78c091e4207b5 +size 5335722980 diff --git a/model-00049-of-00054.safetensors b/model-00049-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a7594cd375d6e7e1092a3f080c18db0c170ab83 --- /dev/null +++ b/model-00049-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a8c6bc3099faf9d5bd97c73c7462536950adebba6592b64069d36758f070908 +size 5363247191 diff --git a/model-00050-of-00054.safetensors b/model-00050-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ef07c3c9454199d73cdc90a30a138a496022b7d --- /dev/null +++ b/model-00050-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329ecda84031f10efa9c8e4945cfb820bb0e27f6b8013cb3f64da148aa5f9308 +size 5294546489 diff --git a/model-00051-of-00054.safetensors b/model-00051-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f26ad02bec2183bbb37b2415ee9b2589ede915b9 --- /dev/null +++ b/model-00051-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab133165375e95fd47fb6ca30bceba894e4ebfdf1d46ffd47eb656fdd2a6c4ff +size 5335722964 diff --git a/model-00052-of-00054.safetensors b/model-00052-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13f5d4156de63d3d0fa5b7c335cf47fe171eba03 --- /dev/null +++ b/model-00052-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c340b8b5cf0b78e15dbdf2fa4697857a55c9a660d50d5d8b8d713c577786c4b +size 5363247191 diff --git a/model-00053-of-00054.safetensors b/model-00053-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7eb725f1384fea910c57ee9c20c1b743046e342 --- /dev/null +++ b/model-00053-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89019491f82279e8c39d09db2cb00463aae5665b5b461fb5ca24825eaa8cdb30 +size 5294546487 diff --git a/model-00054-of-00054.safetensors b/model-00054-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f671105db628c08987913ea8d14a8d902d739ba8 --- /dev/null +++ b/model-00054-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d9c7b497558f341a58d5363e30f1c21c62124c5cfb95d1c10ef2ffba0451ad +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/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..2f90e1190a0ea9ebdf15676b13617b3d7c222d28 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ccf2252fe9cd23ada23a829ec409aab397dbd2ac4f372d3a1a23d1f7c72d6b +size 19970686 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..864b3c6ddf2c21a279ca02108f16df5d5e7d37e2 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,64 @@ +{ + "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|>", + "", + "" + ], + "backend": "tokenizers", + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_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|>", + "", + "" + ], + "is_local": true, + "model_max_length": 128000, + "model_specific_special_tokens": {}, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "TokenizersBackend", + "tool_parser_type": "glm47" +}