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..de54ccf04ea1c4aa1684131db04baaf0f9f49593 --- /dev/null +++ b/README.md @@ -0,0 +1,42 @@ +--- +base_model: +- zai-org/GLM-4.5-Air +- ApocalypseParty/derestricted-iceblink +library_name: transformers +tags: +- mergekit +- merge + +--- +# v3c + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method. + +### Models Merged + +The following models were included in the merge: +* [zai-org/GLM-4.5-Air](https://huggingface.co/zai-org/GLM-4.5-Air) +* [ApocalypseParty/derestricted-iceblink](https://huggingface.co/ApocalypseParty/derestricted-iceblink) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: ApocalypseParty/derestricted-iceblink + - model: zai-org/GLM-4.5-Air +merge_method: slerp +base_model: zai-org/GLM-4.5-Air +parameters: + t: [0, 0, 0.1, 0.15, 0.2] +dtype: bfloat16 +out_dtype: bfloat16 +tokenizer: + source: base +``` 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..87da00b197f1e731ec6b08c29caa92fa23e85585 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 1, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10944, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1408, + "n_group": 1, + "n_routed_experts": 128, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 1.0, + "tie_word_embeddings": false, + "topk_group": 1, + "transformers_version": "4.57.3", + "use_cache": true, + "use_qk_norm": false, + "vocab_size": 151365 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..536c7f995279aea3edf8707f7e460db6c1a3e01b --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,11 @@ +models: + - model: ApocalypseParty/derestricted-iceblink + - model: zai-org/GLM-4.5-Air +merge_method: slerp +base_model: zai-org/GLM-4.5-Air +parameters: + t: [0, 0, 0.1, 0.15, 0.2] +dtype: bfloat16 +out_dtype: bfloat16 +tokenizer: + source: base \ No newline at end of file diff --git a/model-00001-of-00043.safetensors b/model-00001-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f42ec8d3d88193901891f8f65042d502a3c93df --- /dev/null +++ b/model-00001-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13134081d8f1120d9dd1ec8f87a390aa9f83fe86c762e2947a271d752a57e6c +size 4997147776 diff --git a/model-00002-of-00043.safetensors b/model-00002-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33fac954852db0e8dac99414420fa6cf733669c9 --- /dev/null +++ b/model-00002-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c1e9e94c65eeceff520d0678138d96b3a85cb95a78c25f5396e7399d419ed51 +size 4994465648 diff --git a/model-00003-of-00043.safetensors b/model-00003-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08ba8eb3f9575f6dceb98a19ea6886b665af28e1 --- /dev/null +++ b/model-00003-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634726de08a66fae8ad2002878c63354ff661193936964b260e0fd48881c9713 +size 4994465872 diff --git a/model-00004-of-00043.safetensors b/model-00004-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..721b612fd774b3736378f49fe1e02f3f27229641 --- /dev/null +++ b/model-00004-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5006d34a835f2b66202183dce014aa5111eb692d5a6ed7f78100afa256209875 +size 4994465872 diff --git a/model-00005-of-00043.safetensors b/model-00005-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..894951ccd2217dd1108a4a5de14e38ba7184b97e --- /dev/null +++ b/model-00005-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7bbf693c5043d90987a7b3a7e3ba0e9a8e3ba055cfa39c7e034155f21f31013 +size 4994465872 diff --git a/model-00006-of-00043.safetensors b/model-00006-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34f0e28e5bfe063be3b577954c4ea9de8d942da6 --- /dev/null +++ b/model-00006-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a998a25706d3b36dba8b7226641650d13b5e3ef3c2f134f871634a0fcf55ad +size 4994465872 diff --git a/model-00007-of-00043.safetensors b/model-00007-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bbe1a7c21a6862726c6a99e6e4c271f36cabd1c6 --- /dev/null +++ b/model-00007-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4133acf358b5a4dff9e6b708d2427879be360772877d59f0b366d43549a7a18 +size 4994465872 diff --git a/model-00008-of-00043.safetensors b/model-00008-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff109fdef320f1d3f31cd969c3f2d97197d6c076 --- /dev/null +++ b/model-00008-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af580d89d37bdf2033081c45c0a18b250fef050a1d69e9eaf10d41a5232d8f1e +size 4994465888 diff --git a/model-00009-of-00043.safetensors b/model-00009-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc046ddb46dce920df92a742055feecd51b853cf --- /dev/null +++ b/model-00009-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affa2f27282813f2f85192df0d212e5b6d7e3d3e2a4c1c85c283fb17cef036b1 +size 4946241848 diff --git a/model-00010-of-00043.safetensors b/model-00010-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e91d86603cb5e0d78453f8f4472b321a72345eaf --- /dev/null +++ b/model-00010-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa619f90bce8cfbc5e9cc2176fa63dcf2ef7e8797263419ade4332077683b03 +size 4996596312 diff --git a/model-00011-of-00043.safetensors b/model-00011-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f365331b25ac99d45d1d327fed8352b004673ad8 --- /dev/null +++ b/model-00011-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1690ba0a9c26edc53515bfa3f76b6e49b4c6085c88d5e520775c280c4cd32141 +size 4994465864 diff --git a/model-00012-of-00043.safetensors b/model-00012-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fdf4ad8e61df3d02b31092a183fa4878a470a67c --- /dev/null +++ b/model-00012-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add8176f86dff3a7d277653c96794a55ff76c1a71223ae5e12e071a78ba45a6d +size 4994465536 diff --git a/model-00013-of-00043.safetensors b/model-00013-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8102ed032760fc8ad820dd5a6638461bc67611d5 --- /dev/null +++ b/model-00013-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624532dc031c8760933349943bb45aad4285edd70e1b5ce883ff90725d7c167f +size 4994465896 diff --git a/model-00014-of-00043.safetensors b/model-00014-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6661b98bc1fba47d474c83a01e461095ab8a042 --- /dev/null +++ b/model-00014-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42df9a864509a193e817dca4577ef560d775c1b4f66c5a56be8e4eac1ccaaccc +size 4994465880 diff --git a/model-00015-of-00043.safetensors b/model-00015-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d6a11656e22d58c15df80330465b5d2d8e917738 --- /dev/null +++ b/model-00015-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feaeb2264eaeb12d187e385b78fe610ae6e36517c65abaf0aca376def8d4bcb1 +size 4994465872 diff --git a/model-00016-of-00043.safetensors b/model-00016-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87070f43a48b2d7873a7f8a03f1c3a759491669f --- /dev/null +++ b/model-00016-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df3515807a6c31a3ac59f4ca4165857ea070d28c891e3c396e63404ee228bd8 +size 4994465872 diff --git a/model-00017-of-00043.safetensors b/model-00017-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44e1c220b5077dd78b8fb621e032e4f747dfbdc2 --- /dev/null +++ b/model-00017-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2592200430ceccaa60c541381ee6fe0976273b57a928de84875ee6e49a8a306 +size 4994465872 diff --git a/model-00018-of-00043.safetensors b/model-00018-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..929b09fd10b52daf45ef7d7c01c145d21c19b4d2 --- /dev/null +++ b/model-00018-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54e0ccb9971d622c36193057a8463a7142feab668fb38980181b6c400ba233b +size 4994465872 diff --git a/model-00019-of-00043.safetensors b/model-00019-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9ced34d2a52e09f8489d3efd4660006f3440fbd --- /dev/null +++ b/model-00019-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b765260c13405ca9e21ee85679cca45a8f655cf1259f1688ad94e8e39fd07d +size 4994465872 diff --git a/model-00020-of-00043.safetensors b/model-00020-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2afc55a1692ca79215bc4b4ed23d6a377d67510f --- /dev/null +++ b/model-00020-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c097fe1a00127e52a0fdce8e26ab45f10930bab03ade0e0e0b102aaabb74cbb1 +size 4994465872 diff --git a/model-00021-of-00043.safetensors b/model-00021-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f5b6f13c52e46f58c8cc3c4844aa9288ed577c30 --- /dev/null +++ b/model-00021-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f44e34d3442429c5cdd32da4d3fcae017719d1e7759918b7f33922273236f6 +size 4994465872 diff --git a/model-00022-of-00043.safetensors b/model-00022-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..70d833df3ce3d2ffe3148d15c16fed29b673d9da --- /dev/null +++ b/model-00022-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5633347f553a19c66c9fbfbda9ab2b99f946b3a044950f8b88061efef2ff6f33 +size 4994465536 diff --git a/model-00023-of-00043.safetensors b/model-00023-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dad810fdf3d4bcc04bafcbbad969d4d6980e79ca --- /dev/null +++ b/model-00023-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8daec20c72543fd4c3ba549eca24564c251d281fb950828ed171bc5d857648b8 +size 4994465824 diff --git a/model-00024-of-00043.safetensors b/model-00024-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69b20ce984da91a59eea37cce7b702273cb4155c --- /dev/null +++ b/model-00024-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036661e120b5beb2e44f3c04b2bc9ab1c6762714e1aff2a869e5e39dabd53619 +size 4995525432 diff --git a/model-00025-of-00043.safetensors b/model-00025-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48cbb88174901bef40b04342379f3ecff009b235 --- /dev/null +++ b/model-00025-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa5392eda6a9a55b27b3666584442a73a0a6084b316fb38473c0a4f4a949a1f +size 4993450568 diff --git a/model-00026-of-00043.safetensors b/model-00026-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30e3ca96ba498c13889eca7a76f52e51564a9d6e --- /dev/null +++ b/model-00026-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0788f9f2ff68a89e3fb4b9e276fdabde332447ffa8e3b7d0a7b7c3bbcd6293b9 +size 4994465896 diff --git a/model-00027-of-00043.safetensors b/model-00027-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7af7d903d520136907381c48fa35b9e9bb66cde0 --- /dev/null +++ b/model-00027-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:991fe08482eef16e340c683b3aec88cdffc740d67bfee2ac28a214a78c39cbf1 +size 4994465896 diff --git a/model-00028-of-00043.safetensors b/model-00028-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cee7c4270262b9be7d598ebfe6b54b58be29670 --- /dev/null +++ b/model-00028-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31953c40e58d9c7920f842da6b35ef31f6f46326bf343337f7cbd07d139e96e4 +size 4994465896 diff --git a/model-00029-of-00043.safetensors b/model-00029-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98884d0587b5fd8fd004d13f8b7e4e4d78037f6a --- /dev/null +++ b/model-00029-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5b4d1f8a334bcea90b0845f11bef81a993c5f23013737597c7997efe32c157 +size 4994465880 diff --git a/model-00030-of-00043.safetensors b/model-00030-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9163e15b369047babde592701f627bf2ffae7888 --- /dev/null +++ b/model-00030-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d423d881d4abff21f7e553d275f237f0a22a7db9d3bb4f009147fb0579d546a +size 4994465872 diff --git a/model-00031-of-00043.safetensors b/model-00031-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57c3812a3c285dfda76f7933b98fc4824b8e80e9 --- /dev/null +++ b/model-00031-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df4877fd63135c15ae715e038a686c4d350ee95f449f4fa6ae8fc4952039669 +size 4994465872 diff --git a/model-00032-of-00043.safetensors b/model-00032-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9024aedbeaa4e30868e99b79df2e84c1edd6b078 --- /dev/null +++ b/model-00032-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a7219094cfc6af670277c8c823e16f55408b105497085563e25cb9796b21e82 +size 4994465672 diff --git a/model-00033-of-00043.safetensors b/model-00033-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b91704d9f5d3a33661365af4ad046e593f55924 --- /dev/null +++ b/model-00033-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc40480b049319bb23f841e48810ccc9df9c89808e3f71290978081788f4563 +size 4994465672 diff --git a/model-00034-of-00043.safetensors b/model-00034-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6cb96034dc3c2d4ea8d1ce341bded2f89736d98a --- /dev/null +++ b/model-00034-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6e172a9de032f02e327718e924a7ac97874f9a94c99b9ab14d5860ec2ceb39 +size 4994465872 diff --git a/model-00036-of-00043.safetensors b/model-00036-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..103b3a039b15093aaaac26b89ac15ae3ee06467b --- /dev/null +++ b/model-00036-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9271406b6292f3fb5221c3d34767019eab69f5aaaceacc673eb5946404c870 +size 4994465872 diff --git a/model-00037-of-00043.safetensors b/model-00037-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..774eabe99275485aa4cf5f7f7e6fa1ea12bffb19 --- /dev/null +++ b/model-00037-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0cf18b4ff902bbfa9f10c22ece66d4ae182678b2430d7917729709691db078c +size 4994465864 diff --git a/model-00038-of-00043.safetensors b/model-00038-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ad67556c20b496c214ac9f5e54588c053f2dca4 --- /dev/null +++ b/model-00038-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f054f99b28da40444739e34fa792f45b88e99cb520c30f366db17e9239d70ff6 +size 4994465888 diff --git a/model-00039-of-00043.safetensors b/model-00039-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ebea5a665229a4ea4ba60b19a8511146153a4439 --- /dev/null +++ b/model-00039-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7896a86358518aa44555dd238a86955c967c6ebe96abe8eff15952f0b504b6f7 +size 4995514568 diff --git a/model-00040-of-00043.safetensors b/model-00040-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8889917e080dfdde36230cbf9216fb0e7274cd50 --- /dev/null +++ b/model-00040-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1220c3eb2363e38e26ce4fdc1d844a4dda5d179b5000441e867f0dfe9875d84 +size 4993460624 diff --git a/model-00041-of-00043.safetensors b/model-00041-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d18e8898ecf88d7a8a93124bc811f4c706d8ad8f --- /dev/null +++ b/model-00041-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feca05b18cea78de4c487e8607a2c03288e2912bda6ae551cd95c3bb33bf55f7 +size 4994465472 diff --git a/model-00042-of-00043.safetensors b/model-00042-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a4eefcbac3470cf446c1d29bbc54ae1158e98dd --- /dev/null +++ b/model-00042-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846e433a31e4362889ce076ad81cdabadcd6a5a1a1354c535e0aa970803fff3d +size 4994465472 diff --git a/model-00043-of-00043.safetensors b/model-00043-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35fea0f2b655dbee1e1b1fec5a190430e3951a10 --- /dev/null +++ b/model-00043-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:943c7946255b3fe137cab36e5eb0ac1312f7cc77605eb020df06c58af21e9149 +size 3979432872 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..be559a0015d6ead027c9ef19f6246b226112ee5a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,17933 @@ +{ + "metadata": { + "total_size": 213701438720, + "mergekit_version": "0.1.4" + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00043.safetensors", + "model.embed_tokens.weight": "model-00001-of-00043.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00043.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.gate.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.gate.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.gate.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.gate.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.input_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.gate.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.input_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.gate.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.input_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.gate.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.input_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.gate.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.input_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.gate.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.input_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.gate.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.input_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.gate.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.input_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.gate.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.input_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.gate.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.input_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.gate.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.input_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.gate.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.input_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.gate.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.input_layernorm.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.gate.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.input_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.gate.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.input_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.gate.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.input_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.gate.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.input_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.gate.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.input_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.gate.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.input_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.gate.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.input_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.gate.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.input_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.gate.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.input_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.gate.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.input_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.gate.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.input_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.gate.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.input_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.gate.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.input_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.gate.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.input_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.gate.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.input_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.gate.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.input_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.gate.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.input_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.gate.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.input_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.gate.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.input_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.gate.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.input_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.gate.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.input_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.gate.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.input_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.gate.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.input_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.gate.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.input_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.gate.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.input_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.gate.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00041-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.input_layernorm.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.gate.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.input_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.gate.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00043-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00043-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00043-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00043-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00043-of-00043.safetensors", + "model.norm.weight": "model-00043-of-00043.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" +}