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..b8db1da98223eb4e6d072c295d069a9cb0dea113 --- /dev/null +++ b/README.md @@ -0,0 +1,42 @@ +--- +base_model: +- ApocalypseParty/derestricted-iceblink +- ApocalypseParty/Iceblink-SFT-1-hf +library_name: transformers +tags: +- mergekit +- merge + +--- +# v3b + +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: +* [ApocalypseParty/derestricted-iceblink](https://huggingface.co/ApocalypseParty/derestricted-iceblink) +* [ApocalypseParty/Iceblink-SFT-1-hf](https://huggingface.co/ApocalypseParty/Iceblink-SFT-1-hf) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: ApocalypseParty/derestricted-iceblink + - model: ApocalypseParty/Iceblink-SFT-1-hf +merge_method: slerp +base_model: ApocalypseParty/Iceblink-SFT-1-hf +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..d1a2dec474829cf578a0627194d6a315fce58a32 --- /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": 0, + "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..026e44afeced02059cdcd6d490c3fac814a53149 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,11 @@ +models: + - model: ApocalypseParty/derestricted-iceblink + - model: ApocalypseParty/Iceblink-SFT-1-hf +merge_method: slerp +base_model: ApocalypseParty/Iceblink-SFT-1-hf +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..13e0a31c0b70d5ead14098dcdd283c365c88ad2f --- /dev/null +++ b/model-00001-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42aa64c076d2e9201090b354002ad540fa6a844b338460a1c97e968de318bfb4 +size 4997147776 diff --git a/model-00002-of-00043.safetensors b/model-00002-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..231b36e30f9dbfcbf40a1f44dd2cdd74830aa074 --- /dev/null +++ b/model-00002-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3145e6003288592240bfaff6f50403db922a065b51a8aeb682c16cb29bf0bf1 +size 4994465648 diff --git a/model-00003-of-00043.safetensors b/model-00003-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a49819bd5ce14fb601ca77b0d9cab7d0058598ec --- /dev/null +++ b/model-00003-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4fd49b15bafecd8b3d4f8c970a55ad6d7bf4f16e576c0557b3100591f9dea8a +size 4994465872 diff --git a/model-00004-of-00043.safetensors b/model-00004-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67376c282b7394a8d40c39a8b5d56f38b9faaff7 --- /dev/null +++ b/model-00004-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bfe8bd5003ee226d557a2f2b28386b483f6350b2ad88e8b785b65b4d8e13f9c +size 4994465872 diff --git a/model-00005-of-00043.safetensors b/model-00005-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..851c4eac680d30df6fdd6ef500694f822acee83a --- /dev/null +++ b/model-00005-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1330ed2cfc8b3328b694af1d1c2b02d1ef31117b78f653f530b2630b0596dd1f +size 4994465872 diff --git a/model-00006-of-00043.safetensors b/model-00006-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08309a99bd38ac1bc1ae1cdd82fa87688bde112d --- /dev/null +++ b/model-00006-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ef51aa1b49477b0742972475e6a2cf8f7c9a89e9d14d2f31c5b5916972c80f +size 4994465872 diff --git a/model-00007-of-00043.safetensors b/model-00007-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f61de09fa94ecf031cb540b940d269d7a91c6edc --- /dev/null +++ b/model-00007-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a80232a982d8a18c5b577263fe1e55ac78727058c49a2bc31149434ad2299b2 +size 4994465872 diff --git a/model-00008-of-00043.safetensors b/model-00008-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a271b7da95adb0df4fb2d5219d047505c2461719 --- /dev/null +++ b/model-00008-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433c1a57afd9367ee0eb32e629c321b26b7232c15493ed7b0715a3e21dada0b9 +size 4994465888 diff --git a/model-00009-of-00043.safetensors b/model-00009-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1f220b831667fc0257e35c1f1117c1e618883a3 --- /dev/null +++ b/model-00009-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7aa37925a0340fdfc70c79846c9efc351a9ff48c456378fdba3bdd813f8bc0 +size 4946241848 diff --git a/model-00010-of-00043.safetensors b/model-00010-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..739353a059f001878274bf92de0be025283521af --- /dev/null +++ b/model-00010-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c28fc59d54282504202c1066ca93b8d894a8b273e50d0f0fbe5b49789dd026 +size 4996596312 diff --git a/model-00011-of-00043.safetensors b/model-00011-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3bb91def91450174231cf880529817e1ab49bb81 --- /dev/null +++ b/model-00011-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9846219d4e39d232fad8c66521c23c8b896983b7863e3df01c50d1b25d1429dd +size 4994465864 diff --git a/model-00012-of-00043.safetensors b/model-00012-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..643c0739d56fa21ba684a5f76c6bd3606a728f51 --- /dev/null +++ b/model-00012-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39eaedbcbe22a2931aeea42d637af6c3831268b73cd513f15d19507fb8eb6bd8 +size 4994465536 diff --git a/model-00013-of-00043.safetensors b/model-00013-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..391bc549a6595bc777cadba2537176bf6e27fa38 --- /dev/null +++ b/model-00013-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c1a3ee622f2ca89c7fc1f4d4ae8f5891b19ed9f251fe235cc54ff29d6f2789 +size 4994465896 diff --git a/model-00014-of-00043.safetensors b/model-00014-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b353be025e2b4f0d4051cf8fca3af081c396442 --- /dev/null +++ b/model-00014-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b20869136ad4da873e7bbdcf4e2cfaeb61960b0f6d391d985e85b783ec54027 +size 4994465880 diff --git a/model-00015-of-00043.safetensors b/model-00015-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3529af4ccc9a04037b10fade1d72c996268d8bae --- /dev/null +++ b/model-00015-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9907ca7c7384699b9133190ed610aaadbc62eab1c59d2524664d5298855af18f +size 4994465872 diff --git a/model-00016-of-00043.safetensors b/model-00016-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9aa60fab0cf4b201d186df34bd8dec634b191ba --- /dev/null +++ b/model-00016-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba8d4687532531e5d4f2a467417900dfb1a927b01fc961126082629a85a55068 +size 4994465872 diff --git a/model-00017-of-00043.safetensors b/model-00017-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6dffecbf641c2b35e794a4a44d2740c98b4210f --- /dev/null +++ b/model-00017-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92322dccbc25493443d45c59dd832ba7a65c49020de196d3dd73610fc50dd757 +size 4994465872 diff --git a/model-00018-of-00043.safetensors b/model-00018-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..879d9c4f6952b0a7d9ca0a49fbb7c19aa34afae0 --- /dev/null +++ b/model-00018-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bc675d8ae5e9dad6696f4339875cfd2c91f2f488f0bce0c2ef3280eb91b5a6 +size 4994465872 diff --git a/model-00019-of-00043.safetensors b/model-00019-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90e684c2455ad537e9897fb952dd82f426249e9d --- /dev/null +++ b/model-00019-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abaa1e565a730845cdc61f370ecfb82e2688e0019d2e095ea2b13b1ea4bd5ae1 +size 4994465872 diff --git a/model-00020-of-00043.safetensors b/model-00020-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd9f1a4832739d37937d86e5d0fa1c0e44d10188 --- /dev/null +++ b/model-00020-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b2544e747325173c5bb5313b7c88afee035fd7c768d1415c12e5f9b1f146272 +size 4994465872 diff --git a/model-00021-of-00043.safetensors b/model-00021-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2f12c1cb7c7c2ad5cb511bf38660f5c3445a607 --- /dev/null +++ b/model-00021-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3179f3dd26c591319f166a2afa5524f9feae4904b667adee9526666613dcfa9c +size 4994465872 diff --git a/model-00022-of-00043.safetensors b/model-00022-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e5d24ecc2435070fc175f3a0e1fc4664234c91d --- /dev/null +++ b/model-00022-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2c3477d9f46a8b5e1f1699d92f33cac5a7841b5a6b08d37ffcc36459a01752 +size 4994465536 diff --git a/model-00023-of-00043.safetensors b/model-00023-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8b64b7e68ae9e2167abfa1540529cd1488f9c83 --- /dev/null +++ b/model-00023-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffb5018c00a528f9260316fde54df1771fbea9e10d9297fb9fdddb5333939b8 +size 4994465824 diff --git a/model-00024-of-00043.safetensors b/model-00024-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c1f0036cb4d432495a8cb60ea5e9500d451484d --- /dev/null +++ b/model-00024-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a2ccb51134f501a5e6307663db5655e3f95a80d3b3a1e0aa9384625d0cb289 +size 4995525432 diff --git a/model-00025-of-00043.safetensors b/model-00025-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4afddf3b19d1095bbc2fc03e1fe01b36d835457 --- /dev/null +++ b/model-00025-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379119749bfb4b080a0a7c763bdb423fce261cbe3099df02ac8a36500bcbe226 +size 4993450568 diff --git a/model-00026-of-00043.safetensors b/model-00026-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..491251a3121a978ff15768d1afc79293de945e73 --- /dev/null +++ b/model-00026-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a786857b2eb82acdc5eb3ad64648567f9f2f7926bd9e7450cbaed7fdc676b04 +size 4994465896 diff --git a/model-00027-of-00043.safetensors b/model-00027-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7231b8c2661edf8515dc9427d85782928bbc6a5 --- /dev/null +++ b/model-00027-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ff04c486e46345c0d0bbbdfef48ad51727c907f89669d76b4c46e7cdf1629b +size 4994465896 diff --git a/model-00028-of-00043.safetensors b/model-00028-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7778267a1e44f6e438c13c460acc5bd69ad922ee --- /dev/null +++ b/model-00028-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa34a812092369adcac16502bc21d92925507f943cdf146bc2426024d184fed +size 4994465896 diff --git a/model-00029-of-00043.safetensors b/model-00029-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a27527157a7318ccf6f4a4d7066d7f489222541 --- /dev/null +++ b/model-00029-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aac1f8ac57dca572f0915a1bd3460e878c9a8fc5b29d305fabe920c98274c1d +size 4994465880 diff --git a/model-00030-of-00043.safetensors b/model-00030-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fa3bed91d64c90a6cfda0437ef7c965e14f6cdf --- /dev/null +++ b/model-00030-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7253b960c115bd5ab969564c2694fe2501d4acaed1e721fddaf59440c65aded +size 4994465872 diff --git a/model-00031-of-00043.safetensors b/model-00031-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..599421eaf16d6b2b6d60966dab5ee7cbe139867e --- /dev/null +++ b/model-00031-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d5c01102d79bc5705fa4565912af24e727b24a37391d221dca01068777c77b +size 4994465872 diff --git a/model-00032-of-00043.safetensors b/model-00032-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1494d0149293882b53171c87eb9cb3480809c959 --- /dev/null +++ b/model-00032-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7759e38756d58c2106ec76a96fda24e0f67cf1b8c86f2e42b6cd00d6bb841807 +size 4994465672 diff --git a/model-00033-of-00043.safetensors b/model-00033-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c53a9ea335afde5a8908e4c73af9ab04bf332292 --- /dev/null +++ b/model-00033-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530bfa95ebfd38ba843c9cf5bfcaa525713754099a2528af1ed00376551f313e +size 4994465672 diff --git a/model-00034-of-00043.safetensors b/model-00034-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb5ceda3f22575ae2bafb6b9f95fd3b3dfe95d38 --- /dev/null +++ b/model-00034-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ecc4bf7058ba0a09de57b84a248e22b4ec48dcf48a5e32f538bd6ad0fb49de +size 4994465872 diff --git a/model-00036-of-00043.safetensors b/model-00036-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f0a159f89e51ad792358750b83ff2a943eddac1 --- /dev/null +++ b/model-00036-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49fed7bea347a10a0e51a8829db6711609d24d6150650742844645674181273 +size 4994465872 diff --git a/model-00037-of-00043.safetensors b/model-00037-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..170557b719becd3f887e9b2fa5bd0f0d65524d15 --- /dev/null +++ b/model-00037-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d853538434435f0a6298b3384efc19964a93078eba79123f0db5e4bc158f5088 +size 4994465864 diff --git a/model-00038-of-00043.safetensors b/model-00038-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e289b638fe1a697d15dfa5a14ec506cad7926f5 --- /dev/null +++ b/model-00038-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5590df80774fdb396587f6efd5beefaee632dcd3dcbbb0664e053507b50abac6 +size 4994465888 diff --git a/model-00039-of-00043.safetensors b/model-00039-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aeb3f5f7063c57b31b2628b74c44982ed870821d --- /dev/null +++ b/model-00039-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600444df60d0f3e765652e65b71642f2fcf287994ffb5089d737ca4f6085aae3 +size 4995514568 diff --git a/model-00040-of-00043.safetensors b/model-00040-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06e3eb6aba4bc210f9338590f38004b9c41df787 --- /dev/null +++ b/model-00040-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e93157a22943af414f260f95e8644f21b77588f36b151ad149970d8596031a61 +size 4993460624 diff --git a/model-00041-of-00043.safetensors b/model-00041-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb015f9b1da54c1672c89630b1ff3cf4d5c87fb9 --- /dev/null +++ b/model-00041-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:498c40b12b65d740ba5d02f78158c92f0ac95985eb24d6120934a96ecf7b450b +size 4994465472 diff --git a/model-00042-of-00043.safetensors b/model-00042-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e87972a2a38b42dcbf86e3df4c01d871691347f1 --- /dev/null +++ b/model-00042-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c14bb03d8d4a19d940d250064c8cd115016e46a5d16830ede2ad7858a31cf0d4 +size 4994465472 diff --git a/model-00043-of-00043.safetensors b/model-00043-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a04ddcf7baa1b90223ce07958d704ab72bea848c --- /dev/null +++ b/model-00043-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee72ae7bffeb87d353bfd92a6d1228f5fd522fded2558b3971e0bf8040eb0b68 +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" +}