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..2cf24ea5f08f816ca4c809241a207225fefce4a1 --- /dev/null +++ b/README.md @@ -0,0 +1,16 @@ +--- +language: +- en +- zh +library_name: mlx +license: mit +pipeline_tag: text-generation +tags: +- mlx +base_model: zai-org/GLM-4.6 +--- + +This model [finding1/GLM-4.6-MLX-8.5bpw](https://huggingface.co/finding1/GLM-4.6-MLX-8.5bpw) was +converted to MLX format from [zai-org/GLM-4.6](https://huggingface.co/zai-org/GLM-4.6) +using mlx-lm version **0.28.0** [plus pull request #494](https://github.com/ml-explore/mlx-lm/pull/494) with +`mlx_lm.convert --quantize --q-bits 8 --hf-path zai-org/GLM-4.6 --mlx-path GLM-4.6-MLX-8.5bpw`. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..41478957aca7a04b7321022e7d1f73de5badd995 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{{ visible_text(m.content) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson(ensure_ascii=False) if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '\n' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..438268f1a2eeff6318264d9df7a54f38a95c326f --- /dev/null +++ b/config.json @@ -0,0 +1,53 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 3, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 202752, + "model_type": "glm4_moe", + "moe_intermediate_size": 1536, + "n_group": 1, + "n_routed_experts": 160, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 92, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "quantization": { + "group_size": 64, + "bits": 8, + "mode": "affine" + }, + "quantization_config": { + "group_size": 64, + "bits": 8, + "mode": "affine" + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 2.5, + "tie_word_embeddings": false, + "topk_group": 1, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.0", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f51194759eb31dde6fbc75a28e3fb7036f68161a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "temperature": 1.0, + "transformers_version": "4.56.2" +} diff --git a/model-00001-of-00090.safetensors b/model-00001-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b738134c98d980177b98fbdcb26d12ddd6384e47 --- /dev/null +++ b/model-00001-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c44ef5e5ebf1d89b774f03e11e04e455ca7889311ccaad9efd492e1bfc854d1 +size 4679461143 diff --git a/model-00002-of-00090.safetensors b/model-00002-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35fd91a48715924e85b17c541fe3f6d3fbc2f319 --- /dev/null +++ b/model-00002-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6cb0a2982b63a781858ddfa35f2ab396be974e0e0c87fbb382a5b5f2c263d1 +size 4182398682 diff --git a/model-00003-of-00090.safetensors b/model-00003-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d91d775208b652c127158d153a51851e027f8a72 --- /dev/null +++ b/model-00003-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a734329db7aa1d17ce900535e7abcf414a8d48d90aea38eadae1f4c5a741b58c +size 4182398676 diff --git a/model-00004-of-00090.safetensors b/model-00004-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5bc0886ce64a5708dbcfe025edebb1ba390a3ba9 --- /dev/null +++ b/model-00004-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fea95d9fd3a8bad25749c6ca6752cdd2d9ea0b71f32b06e8acc9cb801bdc11a +size 4182398694 diff --git a/model-00005-of-00090.safetensors b/model-00005-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56259091e68f11395471c83a4e2dfd158df7bb5d --- /dev/null +++ b/model-00005-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c18aaba7384c5949dee4277f500610fb36468b4ad6f76503505e8c2d51b95a97 +size 4182398684 diff --git a/model-00006-of-00090.safetensors b/model-00006-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8d8d4faa4225fddf3d519fa18bb7ad8ca4a0ab4 --- /dev/null +++ b/model-00006-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf84db00441f0896866f7e10f77d35373c3cc83e89c6ee658b1302169a88668 +size 4182398686 diff --git a/model-00007-of-00090.safetensors b/model-00007-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ea63777f6e929d361bd7d5a9edaecb8af7d85d0 --- /dev/null +++ b/model-00007-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5905d2e46e27246958570bd82d222f939d5e12327248561a391bc82f09a0bb66 +size 4182398666 diff --git a/model-00008-of-00090.safetensors b/model-00008-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57b932af63769da511b843c95d1a757f319fb4f9 --- /dev/null +++ b/model-00008-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f22c2de236d0080e64cb346fc6dfc26f5e25d78eb3346198eeca80024bade3f +size 4182398717 diff --git a/model-00009-of-00090.safetensors b/model-00009-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a017e2b314b67d9c247f5aed64948da16dc72eb3 --- /dev/null +++ b/model-00009-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731bd44f94fb0b74193a78a8c45ceb68646b695d627e761570c2a8ef7fcefec3 +size 4182398733 diff --git a/model-00010-of-00090.safetensors b/model-00010-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eda0508bd8e4960b306b83cfdb32ffd16b14e5ff --- /dev/null +++ b/model-00010-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:543bc8ce253752236300d0d9288824b647bd5ece5bc8aac22dffcc183007fc04 +size 4182398683 diff --git a/model-00011-of-00090.safetensors b/model-00011-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0ce685a16fa06e88136dcf7c336c1caf31e73d4f --- /dev/null +++ b/model-00011-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c2a584e642c77eed23ea9f8dd1eb16f714eecad35001f0aded67e56507d151 +size 4182398699 diff --git a/model-00012-of-00090.safetensors b/model-00012-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfb169c91a4a29e32a6d14365a293e669e52882f --- /dev/null +++ b/model-00012-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600c8eaef2ce98d1b55abb8fed1d026bf863236b7d445c405284e1be0da723a2 +size 4182398709 diff --git a/model-00013-of-00090.safetensors b/model-00013-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2670cd350f41dfa98cfb937b0778064fd24a96e1 --- /dev/null +++ b/model-00013-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b64cb7586c38935436113ef565bb76f401ccd29280c7b406357472522a2d96d +size 4182398697 diff --git a/model-00014-of-00090.safetensors b/model-00014-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..522b8fe3e1145d6616ad12a2d877bab4ecc5eb94 --- /dev/null +++ b/model-00014-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61bf9ba098c2a2ef09035fafe36e7a078c063c0c5db6cd97212ab8626f3696f8 +size 4182398713 diff --git a/model-00015-of-00090.safetensors b/model-00015-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..abb30e29ba40770c9424e71fc977b3d9e83d6adf --- /dev/null +++ b/model-00015-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f2131c2245de03459c58e462cfed2324411e72a91ff129b7631856ef85f558 +size 4182398723 diff --git a/model-00016-of-00090.safetensors b/model-00016-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60a0f2e8ab5cb4dea17abf00959155deaeb19b65 --- /dev/null +++ b/model-00016-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11b4f9a74e7197e43c8005f58c8ac8a2c1c1f8e971d75e9f4d0812d4801a6d8 +size 4182398697 diff --git a/model-00017-of-00090.safetensors b/model-00017-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc0e7badf99a7f745ddcea8cb91d37d40e5ed41b --- /dev/null +++ b/model-00017-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8094acf99d28241f204c11571cd55439b346569796005c7718279ae8bc4defdc +size 4182398729 diff --git a/model-00018-of-00090.safetensors b/model-00018-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eecf3e47fb8e9db54d5b7b9d17e195b3b8ebf80e --- /dev/null +++ b/model-00018-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1c7d69d1508897e48a0b85a2510c7e47184c273c85774fee7fe84d2216537d +size 4182398689 diff --git a/model-00019-of-00090.safetensors b/model-00019-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c295d93197c28733db2b2e383093948a1ba74e0 --- /dev/null +++ b/model-00019-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c9f0fed849590e4b385873282c49da718767a49e5fa7a662100b406ada6b9a +size 4182398729 diff --git a/model-00020-of-00090.safetensors b/model-00020-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..322d53f1fe7949d248bd5250fda23084cc327c40 --- /dev/null +++ b/model-00020-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbebf5e9011ccbcff9aea192c83889626e57f274d26424736b934442e2b6b69 +size 4182398729 diff --git a/model-00021-of-00090.safetensors b/model-00021-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..865c3cca93fa8de10cb4ba6aa9ca8fca04a86d3f --- /dev/null +++ b/model-00021-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa6fea69d6e521c9c23ef89f822914e8e297c7cff4400554aa69c722a9a3148 +size 4182398729 diff --git a/model-00022-of-00090.safetensors b/model-00022-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e678fecf3bafdaf2059e296585b554db5eeb251b --- /dev/null +++ b/model-00022-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de080298cad4c342b69f0e888fc327574099380b62196104c93f37245986024f +size 4182398681 diff --git a/model-00023-of-00090.safetensors b/model-00023-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..72d4be1ea7d0055b45456f42b9bad73a13eee9f0 --- /dev/null +++ b/model-00023-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78e257a5a8101451e766ec4025842b9618469708f136466b7982b156e36c2dc +size 4182398729 diff --git a/model-00024-of-00090.safetensors b/model-00024-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..382267de851a6534486cc9d62dae64369a6c92f3 --- /dev/null +++ b/model-00024-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2625048ca1013b350f2a2db7d6ddb3ce9662821c8028545b0d26ea714fcbf0 +size 4182398711 diff --git a/model-00025-of-00090.safetensors b/model-00025-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1ee7a95063ac7ed1040ac6c5bab3a88363cdf2e --- /dev/null +++ b/model-00025-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3700d4c753cb2a830bfb1757b647d4467063ddea8103cd967c8732308e4d96ca +size 4182398729 diff --git a/model-00026-of-00090.safetensors b/model-00026-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3dd470105e181fdcd9851bab7d0405d3f7f8fd3 --- /dev/null +++ b/model-00026-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f4637d0c214404896939850335f8f87c71966c368255f9b8dc21b00b934330 +size 4182398729 diff --git a/model-00027-of-00090.safetensors b/model-00027-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1af9989120ca323698309cbb989553d40de6c963 --- /dev/null +++ b/model-00027-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e7be5050859003c5e4159fac12994ff0c72c769f9c87e3542ade38936eb8ab +size 4182398729 diff --git a/model-00028-of-00090.safetensors b/model-00028-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0113a8e1bf2d57fab00d6832d6d95c392f17a158 --- /dev/null +++ b/model-00028-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29aa8fd6cb8c7d51af8a610b3fbacda58e7b0fbf52b65becd29610b64881d21 +size 4182398693 diff --git a/model-00029-of-00090.safetensors b/model-00029-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dbb814b0168a0f466ec70244ae827a3c70388f71 --- /dev/null +++ b/model-00029-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac2961ffd51d8216172a95148ad412e3932bb82956dcb07773decca6e5c8e40 +size 4182398723 diff --git a/model-00030-of-00090.safetensors b/model-00030-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b035c2161b541c36e3e225a020ca4c11af852ce --- /dev/null +++ b/model-00030-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd97d3d94982084be63c652ec558be7261d10d2b1216b424015f11c159e04571 +size 4182398729 diff --git a/model-00031-of-00090.safetensors b/model-00031-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d469442d0e5f2b56987d27fc6dc098702d44aa3f --- /dev/null +++ b/model-00031-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd187409a7322609b71c061e577a06d754abf3ebbcd5371604cb9199739a487d +size 4182398721 diff --git a/model-00032-of-00090.safetensors b/model-00032-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8403d62b45d8bf5edae9506f6a083315b2ca10c5 --- /dev/null +++ b/model-00032-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd9ac120a1dfc9ff8ec6bfcb4d016d958878086b0b712ede9ea8cbfab508ab3 +size 4182398721 diff --git a/model-00033-of-00090.safetensors b/model-00033-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb8739678abc1da9054a3e56771d7b2512e2aa0a --- /dev/null +++ b/model-00033-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03ec715960a29ddef4c0e2f2545d333407deb4e0f430b802ac023f4622d088ce +size 4182398729 diff --git a/model-00034-of-00090.safetensors b/model-00034-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c2252fb477a39a8d5e3e00e7a6167f77b267fdd --- /dev/null +++ b/model-00034-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae321de09c080a89699700220f1eb0b9cb9e746015079a063657d1fe5eb8be0 +size 4182398705 diff --git a/model-00035-of-00090.safetensors b/model-00035-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9dbb2b1ec2571c56094afd39fb5df0188e3826bf --- /dev/null +++ b/model-00035-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac08023eb426d4e8a0c4b6e89ef9b10f92d9a79076732fa0d0b117822b804b9 +size 4182398725 diff --git a/model-00036-of-00090.safetensors b/model-00036-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..715d1db3b2bb6a3e9e7d76de83c4c59f97a7edf4 --- /dev/null +++ b/model-00036-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0fc3c91ce64463ebe8fd285d18cb8edf39d9240fdf3ad1a8627b4ebf38790de +size 4182398725 diff --git a/model-00037-of-00090.safetensors b/model-00037-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6155f681bea2208d4519ab4f53734210ce7232c1 --- /dev/null +++ b/model-00037-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48ca8bc2b3228a093b64881a96334fc0b204591f70b043d1f1066b4a62f8807 +size 4182398669 diff --git a/model-00038-of-00090.safetensors b/model-00038-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..106cdbe49ebfc729ea13eed579609a0030e11b31 --- /dev/null +++ b/model-00038-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84970276a03f1315268344fafa5685d9511d1d1c0f313f31a0fc2b1f6b230359 +size 4182398729 diff --git a/model-00039-of-00090.safetensors b/model-00039-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0245bd938e108b06f8cb44d07981e32c7d517f4b --- /dev/null +++ b/model-00039-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b86648895e01959db83ea1f6b8a8d0f9f88c5a347f2bb3ab23cceef03a210aa +size 4182398729 diff --git a/model-00040-of-00090.safetensors b/model-00040-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..537b1db30a8261821e85afeb5c88d6c73efd4a83 --- /dev/null +++ b/model-00040-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b5414c21a628ad7106a4496d303b2b5fd0838ee11abb449945000a5862acde +size 4182398729 diff --git a/model-00041-of-00090.safetensors b/model-00041-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f389ce3fe5f9d519ec8b9c517b6964f8c341c14a --- /dev/null +++ b/model-00041-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55b43da6ae0c9686b9b02125168d8f17c2d69f1f2272693cb5442c323d5269f +size 4182398697 diff --git a/model-00042-of-00090.safetensors b/model-00042-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4f458ba67e5d68c483d90f74db4f6b5a8bf020d --- /dev/null +++ b/model-00042-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c65ada651077626600ded5c9d2cc8176afde4f80f6c186fe5bb83946a3936b +size 4182398729 diff --git a/model-00043-of-00090.safetensors b/model-00043-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aecb594522e7c20817302f0600d4061fab37d561 --- /dev/null +++ b/model-00043-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23f62e27a343dead8d0c0e6a3e2c26bf4f996f992d6966d140beb23e944f80a7 +size 4182398707 diff --git a/model-00044-of-00090.safetensors b/model-00044-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05b24bfa67e7e037de18ed111777dadcd14dd3ec --- /dev/null +++ b/model-00044-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77347bd4e6668e81fafc8bcb378ed4fd1404a11fc3c2a202dd2a2a2e33a1de06 +size 4182398733 diff --git a/model-00045-of-00090.safetensors b/model-00045-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f9eb52252fb9b609e46f5015ca30e54edf73b4a --- /dev/null +++ b/model-00045-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a08f81cde434b19db4ceb3bda2bea45999a7ef0109ac0dbf94774c1f466a7110 +size 4182398705 diff --git a/model-00046-of-00090.safetensors b/model-00046-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d72f190af465b1ed37a5fc369d73eaa94aecefc5 --- /dev/null +++ b/model-00046-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2845ccbaad2f04bc21db33e40dbba23f28da1027af40c2c8c5643eeab45300 +size 4182398691 diff --git a/model-00047-of-00090.safetensors b/model-00047-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dbbc8ccdf54fe6774a523597409bccf490d78775 --- /dev/null +++ b/model-00047-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac867d090d1a9af646340c58cdc69028356fe769e896b91fcb38791a4d1d19e +size 4182398729 diff --git a/model-00048-of-00090.safetensors b/model-00048-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d6d030f5ba05501a4e3bd43fb8dc3e7c197ca68e --- /dev/null +++ b/model-00048-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40840fff7cfc6e0522d6aba70a0d7c0d033776194234890963885facbd76b2f +size 4182398723 diff --git a/model-00049-of-00090.safetensors b/model-00049-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..508db0a9cc38081766b224ffb6fde3b032665ef6 --- /dev/null +++ b/model-00049-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87dc8fbce11cb6572e11172309f9b06d82f7c08673e496d5f62e95717dec24e6 +size 4182398723 diff --git a/model-00050-of-00090.safetensors b/model-00050-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f7cf79980d2deb41e66b5ac30a9d54712abbd76 --- /dev/null +++ b/model-00050-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c595787db22e78dc6b789a25f3755032ded723927238a3d0303d6c1216626e8 +size 4182398687 diff --git a/model-00051-of-00090.safetensors b/model-00051-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f761a9cdddc7a50761611c0125a2be195c73ac6 --- /dev/null +++ b/model-00051-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c3a88a2bf1a8f491b165d485b7667760827c7da9840309f89d469208c81fea +size 4182398725 diff --git a/model-00052-of-00090.safetensors b/model-00052-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a12a7cbe6a8c547f6c9cef99849e52fdfc45127 --- /dev/null +++ b/model-00052-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de19d7bb8b516aebb4fa3a093988ab9f127ce0f9e30bb83d74148eede44eee4 +size 4182398729 diff --git a/model-00053-of-00090.safetensors b/model-00053-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff1891798ade996bfab408a80e9248e0991cd2f7 --- /dev/null +++ b/model-00053-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca093928260f10168901f757d1d324c56f45d87acc6702b0063847e1723c2d83 +size 4182398689 diff --git a/model-00054-of-00090.safetensors b/model-00054-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d3a469b13425ec3095e5ec0fed3c0b3c33ab4de --- /dev/null +++ b/model-00054-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e153b62fed2edd52b2c36ef87c256441931bd240b04654acf162d279f42fc66 +size 4182398729 diff --git a/model-00055-of-00090.safetensors b/model-00055-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82a411e35a6ca51df32ef54a56b8598c789bf658 --- /dev/null +++ b/model-00055-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc081298ae87a8b0f5723bd9acbcfe7c926f5d24601a24f147ee6101a290de0 +size 4182398725 diff --git a/model-00056-of-00090.safetensors b/model-00056-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80b5dbc1ba2bee3baf3571f61e80ff44fe4c5a30 --- /dev/null +++ b/model-00056-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5781454f697e416a9e8ddd57796f9be2d0e6a5c5dde8519820a8fe971e169f44 +size 4182398729 diff --git a/model-00057-of-00090.safetensors b/model-00057-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fec4ab74c0a160c774eddaf20d75108efa4ad317 --- /dev/null +++ b/model-00057-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad96517708bb039ce6e7b3a0497c2d2695527964d756b370cce062ef333db654 +size 4182398729 diff --git a/model-00058-of-00090.safetensors b/model-00058-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b12421c09006326f4ac6a8a22e742ca49bacbcbc --- /dev/null +++ b/model-00058-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae17d75cd542827a47b63a1c787e6a9be9d1dda73b40594ae4bbfdbcffe82960 +size 4182398723 diff --git a/model-00059-of-00090.safetensors b/model-00059-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7580dde7638d06caa5757c03f2e2a0015f2ef1ea --- /dev/null +++ b/model-00059-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e2692961db9c6be8f7c041639713c35df12d9e89eb40d2181729f24f4f2052 +size 4182398725 diff --git a/model-00060-of-00090.safetensors b/model-00060-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..edb1b7c44e818a5a712db1e6bab36a52e10acb6b --- /dev/null +++ b/model-00060-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7798ffa83be03bec7e29bf8a39a340564edadba344e5b080460c8f941e85067 +size 4182398725 diff --git a/model-00061-of-00090.safetensors b/model-00061-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d9664dfe9d1d4a0dc9d2279908cdd8aaa4fab873 --- /dev/null +++ b/model-00061-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0101c85e7afe5e24d05d402e8ceb071f887a9e443b91a110fdc78210514021b3 +size 4182398725 diff --git a/model-00062-of-00090.safetensors b/model-00062-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63336ecfbae5c558cc3436a2ea49de6907a5810b --- /dev/null +++ b/model-00062-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a59db12c437553e49662ee10ba816c6e8ba7c5125baed6a484a0f2dbe8c6b7e +size 4182398729 diff --git a/model-00063-of-00090.safetensors b/model-00063-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd1f50b2eb52a3f3b6f8f6652db3fc498eafbcaf --- /dev/null +++ b/model-00063-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361fa094a5b4626b3b19d6c6d7117ce9a320681e13d8042639f762c4689d3585 +size 4182398729 diff --git a/model-00064-of-00090.safetensors b/model-00064-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e3a31b39f4f765bd714ac130b04cff49a338bed2 --- /dev/null +++ b/model-00064-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a58a53ca7865fa19df540cfa402985bbb978800203b1adbe4de9597e44b20d +size 4182398725 diff --git a/model-00065-of-00090.safetensors b/model-00065-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f229d9fceb4e1c75b2c29a4a29a5b56d1ecd1b9c --- /dev/null +++ b/model-00065-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de8b12d460bfc3fec4b51e0e23cec2a8c48adc091c00155a2091c6feec5f1053 +size 4182398733 diff --git a/model-00066-of-00090.safetensors b/model-00066-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0411e097cb8519273f70d5c35b2cd3c39ccdaf31 --- /dev/null +++ b/model-00066-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccb34eb05bdb96c6cc850399d42222ec069f876f57615a2b2bc4976324479c6 +size 4182398729 diff --git a/model-00067-of-00090.safetensors b/model-00067-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d951722bafd96ed69c5bb47281c0bbe5b4cb4bd8 --- /dev/null +++ b/model-00067-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f02aa2a243dfe7b701d0facb3fb7349b20e0ef55f3703772daa6e1b97f6eb0c +size 4182398725 diff --git a/model-00068-of-00090.safetensors b/model-00068-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69463b4d4d9eb591c38df79e3a14ea38fd310200 --- /dev/null +++ b/model-00068-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5fac2dcd72134fc7040a751a085811d0541ded6e422257e057336926271afb +size 4182398729 diff --git a/model-00069-of-00090.safetensors b/model-00069-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c59ccdfbea711f5da1fefba160a7d4f1c56f29e --- /dev/null +++ b/model-00069-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33117f90e987ee3f37460c9e88c824375e1f5b957ecc8b4bdf35b5eba1e61dc8 +size 4182398729 diff --git a/model-00070-of-00090.safetensors b/model-00070-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45eed00ca2668d8de11f531758dc2fcae4d467db --- /dev/null +++ b/model-00070-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11ab856044ddebd6470230be7a99349e44accc804f6586b817de072e3cd952f +size 4182398733 diff --git a/model-00071-of-00090.safetensors b/model-00071-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a52940998a6b8e053d69005fab284794ac61acc --- /dev/null +++ b/model-00071-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c13e7640481e0e0156fa9fecbe5d831d1a240eb25247e2b5577822e6e88dd93 +size 4182398723 diff --git a/model-00072-of-00090.safetensors b/model-00072-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf46dea5cdf8b20c410caef09583fbc9dc62d2d6 --- /dev/null +++ b/model-00072-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb33d3480e396f83b44b8b6c934427c174bd3c9cf281f3235b4a241d49fa7ae4 +size 4182398729 diff --git a/model-00073-of-00090.safetensors b/model-00073-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2c7260f92f800abfad9c16d4d47bf08c487d55d --- /dev/null +++ b/model-00073-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c16f72206b7df02e18d17d182757e9d672ef92555a610c010b005d9bc9a517a7 +size 4182398733 diff --git a/model-00074-of-00090.safetensors b/model-00074-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fa6580d315d66f9802e1389bb79b2b874480806 --- /dev/null +++ b/model-00074-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e9db3630beb4ff9bdfe93551a3bd6291c2bfc598df05e4fcc56cacfc3f3df1 +size 4182398725 diff --git a/model-00075-of-00090.safetensors b/model-00075-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a52bcf73e86dabac4dc64111f55b16ec7f6d7da --- /dev/null +++ b/model-00075-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4bdcf9b96e91d5f64f5142fee85e82046cdf289a7e845d5f6e021e445ab9a2 +size 4182398729 diff --git a/model-00076-of-00090.safetensors b/model-00076-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e203b0dab375cfe044c00553ebaad9ae21142e2 --- /dev/null +++ b/model-00076-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0702e19c16e1506067538fa8db64fd72fe2c898bfe3d3a775f7876c7a1adc9ac +size 4182398729 diff --git a/model-00077-of-00090.safetensors b/model-00077-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf2205acfac00d9e3b869852cbda1e139fd90f1e --- /dev/null +++ b/model-00077-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2bad6ce852ac7ef7213ac9c34cc431eb996cbc6d9559c65c113ad43eb89c180 +size 4182398721 diff --git a/model-00078-of-00090.safetensors b/model-00078-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b91e9dee2be8977655f6b4dfeb698567e41a5a2a --- /dev/null +++ b/model-00078-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f450ad31feb88b6465a7adb4b3acd683ae7bbb331e6e727682e7ccfc3c16389c +size 4182398733 diff --git a/model-00079-of-00090.safetensors b/model-00079-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30272a4c93fd9ffcfcac854b7f17e4a680c63fb1 --- /dev/null +++ b/model-00079-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e10864153ca6ec5ae5857207437f35a2e982719be0bbf8d77fab9a0d1a8facb3 +size 4182398723 diff --git a/model-00080-of-00090.safetensors b/model-00080-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acc1f4965b6442a239e5707ddab0e23b4b45b63d --- /dev/null +++ b/model-00080-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6abb73014fc3517766132cf0b17f59695e4ae851d612de63d1f08cc79acb9fa6 +size 4182398723 diff --git a/model-00081-of-00090.safetensors b/model-00081-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a9d6d928cf6983d919a325c640db8435bdc1e652 --- /dev/null +++ b/model-00081-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c939e952eb02cd2c4db750c978334c91977dab5b0e8c5b8d144e750847a2a2b +size 4182398729 diff --git a/model-00082-of-00090.safetensors b/model-00082-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb1d21055ddf7714fd827d3462da080f80efffd5 --- /dev/null +++ b/model-00082-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a12599a5f4121d7868d3e88a85b982ef505903720d585ef089982498915316e +size 4182398729 diff --git a/model-00083-of-00090.safetensors b/model-00083-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..408df0cda4bfb9f8dc40f93d36a1dc80b018c5bb --- /dev/null +++ b/model-00083-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a15acb57c95605a9e06c6ab180182b9e719f265ef4711ab1eb6e6e1f1672940 +size 4182398725 diff --git a/model-00084-of-00090.safetensors b/model-00084-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71ab99857e4a5ef9d66706265ced80c80f1fe20b --- /dev/null +++ b/model-00084-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a1ecff5e828a501e0d43f1619108578d7cce31bd9322604a3f1dcf33692ab8 +size 4182398723 diff --git a/model-00085-of-00090.safetensors b/model-00085-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc0a7ff5297b74900005fa4afe39f0df3a8cddef --- /dev/null +++ b/model-00085-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c56645f69410975396fc9b7cba421d7408093e685f8098860d8cc2b109e97d +size 4182398697 diff --git a/model-00086-of-00090.safetensors b/model-00086-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f11065317503a8de98f69de27cdc511ce4de1af3 --- /dev/null +++ b/model-00086-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eff70ca47b27a36ea3c7a08e95aecd624c059362fdf0d24ef28c6bbc9ad0f11 +size 4182398725 diff --git a/model-00087-of-00090.safetensors b/model-00087-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb1731e85fb34dbda17353e43cb0765e59dc8662 --- /dev/null +++ b/model-00087-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92de6a98846cc4bcad5a206031fb8902d66d311649423f0dbe39e778cde42af9 +size 4182398717 diff --git a/model-00088-of-00090.safetensors b/model-00088-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c0065c076626ff49ea294b2c699d9f9a4896831 --- /dev/null +++ b/model-00088-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:540dda4231389441d0cc231974e77ce0547e1db371f158a1150ee338bbb7c424 +size 4182398733 diff --git a/model-00089-of-00090.safetensors b/model-00089-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..664a04c71ff13c65ea628b8e8af63d46cb974c80 --- /dev/null +++ b/model-00089-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3934769da2f27fbc3914af2356a51ac324cc6e619676a7e1110b211ade1c231a +size 4182398713 diff --git a/model-00090-of-00090.safetensors b/model-00090-of-00090.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e4087831abf8fae5adc5b692d4d8a986088ab446 --- /dev/null +++ b/model-00090-of-00090.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade16e1788e061f2f4d72da65ad04b799e917ce3bb1bc1bdba9c8cb759c5bd1e +size 2188116903 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5203572f1ebb304a19377289ef40957b4b98fe35 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3570 @@ +{ + "metadata": { + "total_size": 374918233728, + "total_parameters": 352797829024 + }, + "weight_map": { + "lm_head.biases": "model-00090-of-00090.safetensors", + "lm_head.scales": "model-00090-of-00090.safetensors", + "lm_head.weight": "model-00090-of-00090.safetensors", + "model.embed_tokens.biases": "model-00001-of-00090.safetensors", + "model.embed_tokens.scales": "model-00001-of-00090.safetensors", + "model.embed_tokens.weight": "model-00001-of-00090.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.down_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.up_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.down_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.up_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.10.input_layernorm.weight": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.gate.weight": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00090.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.k_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.o_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.q_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.v_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.11.input_layernorm.weight": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.gate.weight": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00090.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.k_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.o_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.q_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.v_proj.biases": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00009-of-00090.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00090.safetensors", + "model.layers.12.input_layernorm.weight": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.gate.weight": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00090.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.k_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.o_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.q_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.v_proj.biases": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00010-of-00090.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00090.safetensors", + "model.layers.13.input_layernorm.weight": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.gate.weight": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00090.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.k_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.o_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.q_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.v_proj.biases": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00011-of-00090.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00090.safetensors", + "model.layers.14.input_layernorm.weight": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.gate.weight": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00090.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.k_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.o_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.q_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.v_proj.biases": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00012-of-00090.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00090.safetensors", + "model.layers.15.input_layernorm.weight": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.gate.weight": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00014-of-00090.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.k_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.o_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.q_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.v_proj.biases": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00013-of-00090.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00090.safetensors", + "model.layers.16.input_layernorm.weight": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.gate.weight": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00015-of-00090.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.k_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.o_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.q_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.v_proj.biases": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00014-of-00090.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00014-of-00090.safetensors", + "model.layers.17.input_layernorm.weight": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.gate.weight": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00016-of-00090.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.k_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.o_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.q_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.v_proj.biases": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00015-of-00090.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00015-of-00090.safetensors", + "model.layers.18.input_layernorm.weight": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.gate.weight": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00017-of-00090.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.k_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.o_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.q_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.v_proj.biases": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00016-of-00090.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00016-of-00090.safetensors", + "model.layers.19.input_layernorm.weight": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.gate.weight": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00090.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.k_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.o_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.q_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.v_proj.biases": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00017-of-00090.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00017-of-00090.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.down_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.up_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.20.input_layernorm.weight": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.gate.weight": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00019-of-00090.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.k_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.o_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.q_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.v_proj.biases": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00018-of-00090.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00090.safetensors", + "model.layers.21.input_layernorm.weight": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.gate.weight": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00020-of-00090.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.k_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.o_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.q_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.v_proj.biases": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00019-of-00090.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00090.safetensors", + "model.layers.22.input_layernorm.weight": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.gate.weight": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00021-of-00090.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.k_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.o_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.q_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.v_proj.biases": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00020-of-00090.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00020-of-00090.safetensors", + "model.layers.23.input_layernorm.weight": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.gate.weight": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00022-of-00090.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.k_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.o_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.q_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.v_proj.biases": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00021-of-00090.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00021-of-00090.safetensors", + "model.layers.24.input_layernorm.weight": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.gate.weight": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00023-of-00090.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.k_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.o_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.q_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.v_proj.biases": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00022-of-00090.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00022-of-00090.safetensors", + "model.layers.25.input_layernorm.weight": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.gate.weight": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00024-of-00090.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.k_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.o_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.q_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.v_proj.biases": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00023-of-00090.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00023-of-00090.safetensors", + "model.layers.26.input_layernorm.weight": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.gate.weight": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00025-of-00090.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.k_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.o_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.q_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.v_proj.biases": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00024-of-00090.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00024-of-00090.safetensors", + "model.layers.27.input_layernorm.weight": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.gate.weight": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00026-of-00090.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.k_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.o_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.q_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.v_proj.biases": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00025-of-00090.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00025-of-00090.safetensors", + "model.layers.28.input_layernorm.weight": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.gate.weight": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00027-of-00090.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.k_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.o_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.q_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.v_proj.biases": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00026-of-00090.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00026-of-00090.safetensors", + "model.layers.29.input_layernorm.weight": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.gate.weight": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00028-of-00090.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.k_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.o_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.q_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.v_proj.biases": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00027-of-00090.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00027-of-00090.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.gate.weight": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00090.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00090.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00090.safetensors", + "model.layers.30.input_layernorm.weight": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.gate.weight": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00029-of-00090.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.k_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.o_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.q_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.v_proj.biases": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00028-of-00090.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00028-of-00090.safetensors", + "model.layers.31.input_layernorm.weight": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.gate.weight": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00030-of-00090.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.k_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.o_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.q_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.v_proj.biases": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00029-of-00090.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00029-of-00090.safetensors", + "model.layers.32.input_layernorm.weight": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.gate.weight": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00031-of-00090.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.k_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.o_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.q_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.v_proj.biases": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00030-of-00090.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00030-of-00090.safetensors", + "model.layers.33.input_layernorm.weight": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.gate.weight": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00032-of-00090.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.k_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.o_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.q_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.v_proj.biases": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00031-of-00090.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00031-of-00090.safetensors", + "model.layers.34.input_layernorm.weight": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.gate.weight": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00033-of-00090.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.k_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.o_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.q_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.v_proj.biases": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00032-of-00090.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00032-of-00090.safetensors", + "model.layers.35.input_layernorm.weight": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.gate.weight": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00034-of-00090.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.k_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.o_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.q_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.v_proj.biases": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00033-of-00090.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00033-of-00090.safetensors", + "model.layers.36.input_layernorm.weight": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.gate.weight": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00035-of-00090.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.k_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.o_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.q_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.v_proj.biases": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00034-of-00090.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00034-of-00090.safetensors", + "model.layers.37.input_layernorm.weight": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.gate.weight": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00036-of-00090.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.k_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.o_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.q_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.v_proj.biases": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00035-of-00090.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00035-of-00090.safetensors", + "model.layers.38.input_layernorm.weight": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.gate.weight": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00037-of-00090.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.k_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.o_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.q_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.v_proj.biases": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00036-of-00090.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00036-of-00090.safetensors", + "model.layers.39.input_layernorm.weight": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.gate.weight": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00038-of-00090.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.k_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.o_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.q_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.v_proj.biases": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00037-of-00090.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00037-of-00090.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.gate.weight": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00090.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.k_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.o_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.q_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.v_proj.biases": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00002-of-00090.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00090.safetensors", + "model.layers.40.input_layernorm.weight": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.gate.weight": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00039-of-00090.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.k_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.o_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.q_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.v_proj.biases": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00038-of-00090.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00038-of-00090.safetensors", + "model.layers.41.input_layernorm.weight": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.gate.weight": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00040-of-00090.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.k_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.o_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.q_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.v_proj.biases": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00039-of-00090.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00039-of-00090.safetensors", + "model.layers.42.input_layernorm.weight": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.gate.weight": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00041-of-00090.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.k_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.o_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.q_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.v_proj.biases": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00040-of-00090.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00040-of-00090.safetensors", + "model.layers.43.input_layernorm.weight": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.gate.weight": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00042-of-00090.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.k_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.o_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.q_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.v_proj.biases": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00041-of-00090.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00041-of-00090.safetensors", + "model.layers.44.input_layernorm.weight": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.gate.weight": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00043-of-00090.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.k_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.o_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.q_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.v_proj.biases": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00042-of-00090.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00042-of-00090.safetensors", + "model.layers.45.input_layernorm.weight": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.gate.weight": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00044-of-00090.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.k_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.o_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.q_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.v_proj.biases": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00043-of-00090.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00043-of-00090.safetensors", + "model.layers.46.input_layernorm.weight": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.gate.weight": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00045-of-00090.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.k_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.o_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.q_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.v_proj.biases": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00044-of-00090.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00044-of-00090.safetensors", + "model.layers.47.input_layernorm.weight": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.gate.weight": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00046-of-00090.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.k_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.o_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.q_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.v_proj.biases": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00045-of-00090.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00045-of-00090.safetensors", + "model.layers.48.input_layernorm.weight": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.gate.e_score_correction_bias": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.gate.weight": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00047-of-00090.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.k_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.o_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.q_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.v_proj.biases": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00046-of-00090.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00046-of-00090.safetensors", + "model.layers.49.input_layernorm.weight": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.gate.e_score_correction_bias": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.gate.weight": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00048-of-00090.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.k_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.o_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.q_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.v_proj.biases": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00047-of-00090.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00047-of-00090.safetensors", + "model.layers.5.input_layernorm.weight": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.gate.weight": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00090.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.k_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.o_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.q_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.v_proj.biases": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00003-of-00090.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00090.safetensors", + "model.layers.50.input_layernorm.weight": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.gate.e_score_correction_bias": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.gate.weight": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00049-of-00090.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.k_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.o_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.q_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.v_proj.biases": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00048-of-00090.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00048-of-00090.safetensors", + "model.layers.51.input_layernorm.weight": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.gate.e_score_correction_bias": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.gate.weight": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00050-of-00090.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.k_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.o_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.q_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.v_proj.biases": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00049-of-00090.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00049-of-00090.safetensors", + "model.layers.52.input_layernorm.weight": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.gate.e_score_correction_bias": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.gate.weight": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00051-of-00090.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.k_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.o_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.q_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.v_proj.biases": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00050-of-00090.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00050-of-00090.safetensors", + "model.layers.53.input_layernorm.weight": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.gate.e_score_correction_bias": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.gate.weight": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00052-of-00090.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.k_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.o_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.q_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.v_proj.biases": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00051-of-00090.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00051-of-00090.safetensors", + "model.layers.54.input_layernorm.weight": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.gate.e_score_correction_bias": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.gate.weight": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00053-of-00090.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.k_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.o_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.q_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.v_proj.biases": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00052-of-00090.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00052-of-00090.safetensors", + "model.layers.55.input_layernorm.weight": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.gate.e_score_correction_bias": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.gate.weight": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00054-of-00090.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.k_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.o_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.q_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.v_proj.biases": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00053-of-00090.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00053-of-00090.safetensors", + "model.layers.56.input_layernorm.weight": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.gate.e_score_correction_bias": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.gate.weight": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00055-of-00090.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.k_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.o_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.q_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.v_proj.biases": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00054-of-00090.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00054-of-00090.safetensors", + "model.layers.57.input_layernorm.weight": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.gate.e_score_correction_bias": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.gate.weight": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00056-of-00090.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.k_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.o_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.q_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.v_proj.biases": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00055-of-00090.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00055-of-00090.safetensors", + "model.layers.58.input_layernorm.weight": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.gate.e_score_correction_bias": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.gate.weight": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00057-of-00090.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.k_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.o_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.q_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.v_proj.biases": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00056-of-00090.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00056-of-00090.safetensors", + "model.layers.59.input_layernorm.weight": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.gate.e_score_correction_bias": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.gate.weight": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00058-of-00090.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.k_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.o_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.q_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.v_proj.biases": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00057-of-00090.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00057-of-00090.safetensors", + "model.layers.6.input_layernorm.weight": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.gate.weight": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00090.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.k_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.o_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.q_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.v_proj.biases": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00004-of-00090.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00090.safetensors", + "model.layers.60.input_layernorm.weight": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.gate.e_score_correction_bias": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.gate.weight": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00059-of-00090.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.k_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.k_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.o_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.o_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.q_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.q_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.v_proj.biases": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.v_proj.scales": "model-00058-of-00090.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00058-of-00090.safetensors", + "model.layers.61.input_layernorm.weight": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.gate.e_score_correction_bias": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.gate.weight": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00060-of-00090.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.k_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.k_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.o_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.o_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.q_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.q_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.v_proj.biases": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.v_proj.scales": "model-00059-of-00090.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00059-of-00090.safetensors", + "model.layers.62.input_layernorm.weight": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.gate.e_score_correction_bias": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.gate.weight": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00061-of-00090.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.k_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.k_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.o_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.o_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.q_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.q_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.v_proj.biases": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.v_proj.scales": "model-00060-of-00090.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00060-of-00090.safetensors", + "model.layers.63.input_layernorm.weight": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.gate.e_score_correction_bias": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.gate.weight": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00062-of-00090.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.k_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.k_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.o_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.o_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.q_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.q_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.v_proj.biases": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.v_proj.scales": "model-00061-of-00090.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00061-of-00090.safetensors", + "model.layers.64.input_layernorm.weight": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.gate.e_score_correction_bias": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.gate.weight": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00063-of-00090.safetensors", + "model.layers.64.self_attn.k_norm.weight": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.k_proj.bias": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.k_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.k_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.o_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.o_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.q_norm.weight": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.q_proj.bias": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.q_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.q_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.v_proj.bias": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.v_proj.biases": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.v_proj.scales": "model-00062-of-00090.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00062-of-00090.safetensors", + "model.layers.65.input_layernorm.weight": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.gate.e_score_correction_bias": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.gate.weight": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00064-of-00090.safetensors", + "model.layers.65.self_attn.k_norm.weight": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.k_proj.bias": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.k_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.k_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.o_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.o_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.q_norm.weight": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.q_proj.bias": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.q_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.q_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.v_proj.bias": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.v_proj.biases": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.v_proj.scales": "model-00063-of-00090.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00063-of-00090.safetensors", + "model.layers.66.input_layernorm.weight": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.gate.e_score_correction_bias": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.gate.weight": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00065-of-00090.safetensors", + "model.layers.66.self_attn.k_norm.weight": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.k_proj.bias": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.k_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.k_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.o_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.o_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.q_norm.weight": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.q_proj.bias": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.q_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.q_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.v_proj.bias": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.v_proj.biases": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.v_proj.scales": "model-00064-of-00090.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00064-of-00090.safetensors", + "model.layers.67.input_layernorm.weight": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.gate.e_score_correction_bias": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.gate.weight": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00066-of-00090.safetensors", + "model.layers.67.self_attn.k_norm.weight": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.k_proj.bias": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.k_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.k_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.o_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.o_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.q_norm.weight": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.q_proj.bias": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.q_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.q_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.v_proj.bias": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.v_proj.biases": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.v_proj.scales": "model-00065-of-00090.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00065-of-00090.safetensors", + "model.layers.68.input_layernorm.weight": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.gate.e_score_correction_bias": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.gate.weight": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00067-of-00090.safetensors", + "model.layers.68.self_attn.k_norm.weight": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.k_proj.bias": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.k_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.k_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.o_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.o_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.q_norm.weight": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.q_proj.bias": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.q_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.q_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.v_proj.bias": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.v_proj.biases": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.v_proj.scales": "model-00066-of-00090.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00066-of-00090.safetensors", + "model.layers.69.input_layernorm.weight": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.gate.e_score_correction_bias": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.gate.weight": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00068-of-00090.safetensors", + "model.layers.69.self_attn.k_norm.weight": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.k_proj.bias": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.k_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.k_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.o_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.o_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.q_norm.weight": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.q_proj.bias": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.q_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.q_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.v_proj.bias": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.v_proj.biases": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.v_proj.scales": "model-00067-of-00090.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00067-of-00090.safetensors", + "model.layers.7.input_layernorm.weight": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.gate.weight": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00090.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.k_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.o_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.q_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.v_proj.biases": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00005-of-00090.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00090.safetensors", + "model.layers.70.input_layernorm.weight": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.gate.e_score_correction_bias": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.gate.weight": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00069-of-00090.safetensors", + "model.layers.70.self_attn.k_norm.weight": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.k_proj.bias": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.k_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.k_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.o_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.o_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.q_norm.weight": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.q_proj.bias": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.q_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.q_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.v_proj.bias": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.v_proj.biases": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.v_proj.scales": "model-00068-of-00090.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00068-of-00090.safetensors", + "model.layers.71.input_layernorm.weight": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.gate.e_score_correction_bias": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.gate.weight": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00070-of-00090.safetensors", + "model.layers.71.self_attn.k_norm.weight": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.k_proj.bias": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.k_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.k_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.o_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.o_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.q_norm.weight": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.q_proj.bias": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.q_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.q_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.v_proj.bias": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.v_proj.biases": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.v_proj.scales": "model-00069-of-00090.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00069-of-00090.safetensors", + "model.layers.72.input_layernorm.weight": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.gate.e_score_correction_bias": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.gate.weight": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00071-of-00090.safetensors", + "model.layers.72.self_attn.k_norm.weight": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.k_proj.bias": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.k_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.k_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.o_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.o_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.q_norm.weight": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.q_proj.bias": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.q_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.q_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.v_proj.bias": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.v_proj.biases": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.v_proj.scales": "model-00070-of-00090.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00070-of-00090.safetensors", + "model.layers.73.input_layernorm.weight": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.gate.e_score_correction_bias": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.gate.weight": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00072-of-00090.safetensors", + "model.layers.73.self_attn.k_norm.weight": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.k_proj.bias": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.k_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.k_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.o_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.o_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.q_norm.weight": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.q_proj.bias": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.q_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.q_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.v_proj.bias": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.v_proj.biases": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.v_proj.scales": "model-00071-of-00090.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00071-of-00090.safetensors", + "model.layers.74.input_layernorm.weight": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.gate.e_score_correction_bias": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.gate.weight": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00073-of-00090.safetensors", + "model.layers.74.self_attn.k_norm.weight": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.k_proj.bias": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.k_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.k_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.o_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.o_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.q_norm.weight": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.q_proj.bias": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.q_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.q_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.v_proj.bias": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.v_proj.biases": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.v_proj.scales": "model-00072-of-00090.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00072-of-00090.safetensors", + "model.layers.75.input_layernorm.weight": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.gate.e_score_correction_bias": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.gate.weight": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00074-of-00090.safetensors", + "model.layers.75.self_attn.k_norm.weight": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.k_proj.bias": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.k_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.k_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.o_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.o_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.q_norm.weight": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.q_proj.bias": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.q_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.q_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.v_proj.bias": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.v_proj.biases": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.v_proj.scales": "model-00073-of-00090.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00073-of-00090.safetensors", + "model.layers.76.input_layernorm.weight": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.gate.e_score_correction_bias": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.gate.weight": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00075-of-00090.safetensors", + "model.layers.76.self_attn.k_norm.weight": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.k_proj.bias": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.k_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.k_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.o_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.o_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.q_norm.weight": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.q_proj.bias": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.q_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.q_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.v_proj.bias": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.v_proj.biases": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.v_proj.scales": "model-00074-of-00090.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00074-of-00090.safetensors", + "model.layers.77.input_layernorm.weight": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.gate.e_score_correction_bias": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.gate.weight": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00076-of-00090.safetensors", + "model.layers.77.self_attn.k_norm.weight": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.k_proj.bias": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.k_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.k_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.o_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.o_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.q_norm.weight": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.q_proj.bias": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.q_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.q_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.v_proj.bias": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.v_proj.biases": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.v_proj.scales": "model-00075-of-00090.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00075-of-00090.safetensors", + "model.layers.78.input_layernorm.weight": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.gate.e_score_correction_bias": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.gate.weight": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00077-of-00090.safetensors", + "model.layers.78.self_attn.k_norm.weight": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.k_proj.bias": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.k_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.k_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.o_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.o_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.q_norm.weight": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.q_proj.bias": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.q_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.q_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.v_proj.bias": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.v_proj.biases": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.v_proj.scales": "model-00076-of-00090.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00076-of-00090.safetensors", + "model.layers.79.input_layernorm.weight": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.gate.e_score_correction_bias": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.gate.weight": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00078-of-00090.safetensors", + "model.layers.79.self_attn.k_norm.weight": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.k_proj.bias": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.k_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.k_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.o_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.o_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.q_norm.weight": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.q_proj.bias": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.q_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.q_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.v_proj.bias": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.v_proj.biases": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.v_proj.scales": "model-00077-of-00090.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00077-of-00090.safetensors", + "model.layers.8.input_layernorm.weight": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.gate.weight": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00090.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.k_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.o_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.q_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.v_proj.biases": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00006-of-00090.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00090.safetensors", + "model.layers.80.input_layernorm.weight": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.gate.e_score_correction_bias": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.gate.weight": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00079-of-00090.safetensors", + "model.layers.80.self_attn.k_norm.weight": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.k_proj.bias": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.k_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.k_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.o_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.o_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.q_norm.weight": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.q_proj.bias": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.q_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.q_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.v_proj.bias": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.v_proj.biases": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.v_proj.scales": "model-00078-of-00090.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00078-of-00090.safetensors", + "model.layers.81.input_layernorm.weight": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.gate.e_score_correction_bias": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.gate.weight": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00080-of-00090.safetensors", + "model.layers.81.self_attn.k_norm.weight": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.k_proj.bias": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.k_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.k_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.o_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.o_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.q_norm.weight": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.q_proj.bias": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.q_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.q_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.v_proj.bias": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.v_proj.biases": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.v_proj.scales": "model-00079-of-00090.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00079-of-00090.safetensors", + "model.layers.82.input_layernorm.weight": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.gate.e_score_correction_bias": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.gate.weight": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00081-of-00090.safetensors", + "model.layers.82.self_attn.k_norm.weight": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.k_proj.bias": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.k_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.k_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.o_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.o_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.q_norm.weight": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.q_proj.bias": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.q_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.q_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.v_proj.bias": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.v_proj.biases": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.v_proj.scales": "model-00080-of-00090.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00080-of-00090.safetensors", + "model.layers.83.input_layernorm.weight": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.gate.e_score_correction_bias": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.gate.weight": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00082-of-00090.safetensors", + "model.layers.83.self_attn.k_norm.weight": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.k_proj.bias": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.k_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.k_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.o_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.o_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.q_norm.weight": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.q_proj.bias": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.q_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.q_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.v_proj.bias": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.v_proj.biases": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.v_proj.scales": "model-00081-of-00090.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00081-of-00090.safetensors", + "model.layers.84.input_layernorm.weight": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.gate.e_score_correction_bias": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.gate.weight": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00083-of-00090.safetensors", + "model.layers.84.self_attn.k_norm.weight": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.k_proj.bias": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.k_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.k_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.o_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.o_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.q_norm.weight": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.q_proj.bias": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.q_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.q_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.v_proj.bias": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.v_proj.biases": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.v_proj.scales": "model-00082-of-00090.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00082-of-00090.safetensors", + "model.layers.85.input_layernorm.weight": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.gate.e_score_correction_bias": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.gate.weight": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00084-of-00090.safetensors", + "model.layers.85.self_attn.k_norm.weight": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.k_proj.bias": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.k_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.k_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.o_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.o_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.q_norm.weight": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.q_proj.bias": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.q_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.q_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.v_proj.bias": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.v_proj.biases": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.v_proj.scales": "model-00083-of-00090.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00083-of-00090.safetensors", + "model.layers.86.input_layernorm.weight": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.gate.e_score_correction_bias": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.gate.weight": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00085-of-00090.safetensors", + "model.layers.86.self_attn.k_norm.weight": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.k_proj.bias": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.k_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.k_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.o_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.o_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.q_norm.weight": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.q_proj.bias": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.q_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.q_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.v_proj.bias": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.v_proj.biases": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.v_proj.scales": "model-00084-of-00090.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00084-of-00090.safetensors", + "model.layers.87.input_layernorm.weight": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.gate.e_score_correction_bias": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.gate.weight": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00086-of-00090.safetensors", + "model.layers.87.self_attn.k_norm.weight": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.k_proj.bias": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.k_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.k_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.o_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.o_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.q_norm.weight": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.q_proj.bias": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.q_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.q_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.v_proj.bias": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.v_proj.biases": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.v_proj.scales": "model-00085-of-00090.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00085-of-00090.safetensors", + "model.layers.88.input_layernorm.weight": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.gate.e_score_correction_bias": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.gate.weight": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00087-of-00090.safetensors", + "model.layers.88.self_attn.k_norm.weight": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.k_proj.bias": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.k_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.k_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.o_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.o_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.q_norm.weight": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.q_proj.bias": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.q_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.q_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.v_proj.bias": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.v_proj.biases": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.v_proj.scales": "model-00086-of-00090.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00086-of-00090.safetensors", + "model.layers.89.input_layernorm.weight": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.gate.e_score_correction_bias": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.gate.weight": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00088-of-00090.safetensors", + "model.layers.89.self_attn.k_norm.weight": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.k_proj.bias": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.k_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.k_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.o_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.o_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.q_norm.weight": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.q_proj.bias": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.q_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.q_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.v_proj.bias": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.v_proj.biases": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.v_proj.scales": "model-00087-of-00090.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00087-of-00090.safetensors", + "model.layers.9.input_layernorm.weight": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.gate.weight": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00008-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00090.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.k_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.o_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.q_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.v_proj.biases": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00007-of-00090.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00090.safetensors", + "model.layers.90.input_layernorm.weight": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.gate.e_score_correction_bias": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.gate.weight": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00089-of-00090.safetensors", + "model.layers.90.self_attn.k_norm.weight": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.k_proj.bias": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.k_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.k_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.o_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.o_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.q_norm.weight": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.q_proj.bias": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.q_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.q_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.v_proj.bias": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.v_proj.biases": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.v_proj.scales": "model-00088-of-00090.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00088-of-00090.safetensors", + "model.layers.91.input_layernorm.weight": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.gate.e_score_correction_bias": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.gate.weight": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.biases": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.scales": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.weight": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.biases": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.scales": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.weight": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.biases": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.scales": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.weight": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.biases": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.scales": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.weight": "model-00090-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00090-of-00090.safetensors", + "model.layers.91.self_attn.k_norm.weight": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.k_proj.bias": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.k_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.k_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.o_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.o_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.q_norm.weight": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.q_proj.bias": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.q_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.q_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.v_proj.bias": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.v_proj.biases": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.v_proj.scales": "model-00089-of-00090.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00089-of-00090.safetensors", + "model.norm.weight": "model-00090-of-00090.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..9028cf84013844f17d7616bdec1d88e977924434 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,40 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ed3c66baf1ec4de61840b0abf02142687bfed8 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba +size 19970700 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..75e11cfb2e0cc09f19391ec2278b4825a4c3fae9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,325 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}