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/Modelfile b/Modelfile new file mode 100644 index 0000000000000000000000000000000000000000..55684add5d0c9993c8e033315e9c58794ec43660 --- /dev/null +++ b/Modelfile @@ -0,0 +1,13 @@ +# ollama modelfile auto-generated by llamafactory + +FROM . + +TEMPLATE """[gMASK]{{ if .System }}<|system|> +{{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|user|> +{{ .Content }}<|assistant|>{{ else if eq .Role "assistant" }} +{{ .Content }}{{ end }}{{ end }}""" + +PARAMETER stop "<|user|>" +PARAMETER stop "<|endoftext|>" +PARAMETER stop "<|observation|>" +PARAMETER num_ctx 4096 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..4b88f59e0139a8b4f846cc56e545d518e351ad74 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 1, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10944, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1408, + "n_group": 1, + "n_routed_experts": 128, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 1.0, + "tie_word_embeddings": false, + "topk_group": 1, + "torch_dtype": "bfloat16", + "transformers_version": "4.56.0.dev0", + "use_cache": true, + "use_qk_norm": false, + "vocab_size": 151552 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..dec3fe2233caaf38502598f29a4f498546246620 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "transformers_version": "4.56.0.dev0" +} diff --git a/model-00001-of-00043.safetensors b/model-00001-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4015330b22debf4285fb3f56aaf4aa97ee3abd25 --- /dev/null +++ b/model-00001-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e4797b923360e45ddd528743082fa3219cf12667c2f77eebc1c32d7a31640b +size 4991854888 diff --git a/model-00002-of-00043.safetensors b/model-00002-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d974704a9bad43fc94993a19fbd371d8f013cb43 --- /dev/null +++ b/model-00002-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12afe30c2d8d2730e857a4eca6d39c1e2278a0949b2b3908694214d5d71ab93c +size 4994465432 diff --git a/model-00003-of-00043.safetensors b/model-00003-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..555bd17f9012a86d0713ad80bb64d8cfd032a316 --- /dev/null +++ b/model-00003-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a94f09da829b707867782634636de19ddfcc905b55e5cae223846d63349c6e24 +size 4994465456 diff --git a/model-00004-of-00043.safetensors b/model-00004-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a60fdb61d94cb6c0f3fa1bcd38bc985c81b8d771 --- /dev/null +++ b/model-00004-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf00c65cc00771a681377c0edbd2e0ce21b684fa4a7d3df747dace683e72860 +size 4994465456 diff --git a/model-00005-of-00043.safetensors b/model-00005-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7102e183f13b03cf4f9911e334a3e11ec20d1f90 --- /dev/null +++ b/model-00005-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c2a264250bdf6a235ba8c92bf49c454a6d969ca2c38d991079774e8f372f2e2 +size 4994465456 diff --git a/model-00006-of-00043.safetensors b/model-00006-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54fbc8ef2cadb608b5430bc861ca0b050bcbc169 --- /dev/null +++ b/model-00006-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ec6d11ea61d088254cf2846957a085b0ae42479a41ef25f3022b9713ada547 +size 4974587472 diff --git a/model-00007-of-00043.safetensors b/model-00007-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..711c324c9b1596e10f33a44baae7a6a7abfd3720 --- /dev/null +++ b/model-00007-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a4c82bcd373a0d503b4dda4234991abcc66634368d6ef422e368a741aab971 +size 4991318688 diff --git a/model-00008-of-00043.safetensors b/model-00008-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69eed892cb1125e0df7e041ea8e4a30b8b924d70 --- /dev/null +++ b/model-00008-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8ac7af722f3f2c1a01c2107fe6c7a2633b05f0b61bc792b053b5d8df1b1925 +size 4994465424 diff --git a/model-00009-of-00043.safetensors b/model-00009-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b390dc0263fb4931ac5e9d8e67c81623a28b474c --- /dev/null +++ b/model-00009-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874b345a9741853533b236d9a29c2cc9087c181157f135c6eed87383a7fb452e +size 4994465544 diff --git a/model-00010-of-00043.safetensors b/model-00010-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c25265fec76903362a37bbd59c86b57066e29b0 --- /dev/null +++ b/model-00010-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f165b5f57fac130f25a95a530c01ffde97447f6fa2ff2afc15813e8abdddee37 +size 4994465856 diff --git a/model-00011-of-00043.safetensors b/model-00011-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d8d9f46d67ed878765afa35424afbc87fa59663 --- /dev/null +++ b/model-00011-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f2499ccf0465de3d08d44f4b6ce8c66a9e5642e19fe34c31450e6b0b59e39a +size 4994465856 diff --git a/model-00012-of-00043.safetensors b/model-00012-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2eee51be84be907879e6fceb24a9b9da6024015 --- /dev/null +++ b/model-00012-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94daf86352642d811cdf7bc0f7f9f7e4576414fefc7da83a101951fa2ef3363 +size 4994465856 diff --git a/model-00013-of-00043.safetensors b/model-00013-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..37f625c0d31222e9a2417184143a26cdb534232c --- /dev/null +++ b/model-00013-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd635fc8d5efa1e854a43526d8130a317a616bedf0e428fd7cd3f2213722f97f +size 4994465856 diff --git a/model-00014-of-00043.safetensors b/model-00014-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..943a35878ba4f1a6e0a9277f21e4161583a0dbb9 --- /dev/null +++ b/model-00014-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f2ed9d8ff91765b8b90a068e8c7f52c9d877ccd0e0b20105bcb3123ffc1994 +size 4994465856 diff --git a/model-00015-of-00043.safetensors b/model-00015-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1cc8332cd04c55e036ef8e4b32a591450dea870f --- /dev/null +++ b/model-00015-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b00197ebaa6f2e26364bdf4dd3d97cbc61d926b7a87bb01a62a199f1f39d113 +size 4994465856 diff --git a/model-00016-of-00043.safetensors b/model-00016-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d9436a53c9da29a61ec5f17aa47c71108dfbb2e5 --- /dev/null +++ b/model-00016-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289b88073a8f7ceff0be0019e89917c435a14450a8e7963c93c65b254c35bb8a +size 4994465856 diff --git a/model-00017-of-00043.safetensors b/model-00017-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e0fa5e869fd05f192af3f2f86694799498976de4 --- /dev/null +++ b/model-00017-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb5cdd007f89b007ebb3c5c8ce07f96758f369cc1ce0f6db2f92c13d5a02284 +size 4994465856 diff --git a/model-00018-of-00043.safetensors b/model-00018-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18f6506fe0df2eb7aa81054b18bc79e988b91805 --- /dev/null +++ b/model-00018-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51324da2985ad06efd6f542425838de311920089cb1e4604df67723b006b4af +size 4994465872 diff --git a/model-00019-of-00043.safetensors b/model-00019-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44757e01096d2f209c7b782096aebf9bdb70613b --- /dev/null +++ b/model-00019-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6476b510a2dda718222b43a727b4992f57fd4b7f0e709eb0dc92d2c62c2a6ff5 +size 4994465880 diff --git a/model-00020-of-00043.safetensors b/model-00020-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d2100ec2103371533ea3569bcb1f4eafe6600fa --- /dev/null +++ b/model-00020-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608a87f4178049fda07770a4f325ec56b443627ebd2b8c0f9d55d2f78dd8948b +size 4994465880 diff --git a/model-00021-of-00043.safetensors b/model-00021-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb9f68838480f6c8705250d66a9dca4237fcb126 --- /dev/null +++ b/model-00021-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca8106d50a7c040763cb253a57df0485fe224337f7a15fdcf9ec537ffddc4a4 +size 4992409512 diff --git a/model-00022-of-00043.safetensors b/model-00022-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbe20bb3db8c9a05fb9114f8905783a843abfc96 --- /dev/null +++ b/model-00022-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:639b27d1245a12ce73d41f95d6a7786708de8c054e51a908cc3bfc72ae83dffa +size 4996566416 diff --git a/model-00023-of-00043.safetensors b/model-00023-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..baf27f389b4221315a824869264236e8db7c1149 --- /dev/null +++ b/model-00023-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7dc654b14e59b3fc4bdceb58077484f29883d0332b43daeb257d8f711a5218 +size 4994465848 diff --git a/model-00024-of-00043.safetensors b/model-00024-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afe6df36bb5ae56baa7dfa937a4b5ee3dfa43d4e --- /dev/null +++ b/model-00024-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0d52d1ff5e6dc6c1a7c5c8c687ed13374443afe914979e8b594c1774c2b16f +size 4994465856 diff --git a/model-00025-of-00043.safetensors b/model-00025-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e0abdb04b0df243655a9900ae6c5abb87762a54a --- /dev/null +++ b/model-00025-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc0dbd2f6dfc1b8be1669371d4b96a09ca3f37e6a4cf92f29a12e508c4a6574d +size 4994465856 diff --git a/model-00026-of-00043.safetensors b/model-00026-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5645c8ec9f7728c76d64e612f80d949d36cb91fb --- /dev/null +++ b/model-00026-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d3855aa6e7b3531f4654953acf1632c0cb4c83eb4664af75aab69fced4b1bc0 +size 4994465856 diff --git a/model-00027-of-00043.safetensors b/model-00027-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aad0d686f7e16ced4c345ddd22879b46f1513b80 --- /dev/null +++ b/model-00027-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbff51133889ad5d7c1e865fdb76eb5e35af51c9f09b312f3b39381c3a68bf4 +size 4994465856 diff --git a/model-00028-of-00043.safetensors b/model-00028-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9548083eb27d0e648258b135361492bfd4499184 --- /dev/null +++ b/model-00028-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8765872659c5f4becbd189db1544c0adb06853ce9a65b02730f3e753c21f7c52 +size 4994465856 diff --git a/model-00029-of-00043.safetensors b/model-00029-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..827d5f7fd7428685ffcb05ea6f8a6ae213848e1f --- /dev/null +++ b/model-00029-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4e4b1cb031324775792656707819a60c35f6ef7903a97577f4810cb7324d3c +size 4994465856 diff --git a/model-00030-of-00043.safetensors b/model-00030-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e420402931c19cb3608ec407bfe3c59bc43e85a7 --- /dev/null +++ b/model-00030-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f345af1337423c9cec05b240896457a597cc96d32c16e4c3db8f597e9c49956 +size 4994465856 diff --git a/model-00031-of-00043.safetensors b/model-00031-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..308616a7ae7abcbeec7d2d1ac8df54691caf8952 --- /dev/null +++ b/model-00031-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3a2528e9bce3553fb6e15c9b8179bb869aff2622ae8d3905efaec25c109176 +size 4994465856 diff --git a/model-00032-of-00043.safetensors b/model-00032-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..505128f106976568f6cfa9108a07dfe9b2a69ffe --- /dev/null +++ b/model-00032-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f87e68ccc54a6352c6696a6638fbb78572f05b023ad527e5e5638ea6cc389d +size 4994465856 diff --git a/model-00033-of-00043.safetensors b/model-00033-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea713a9b3cf05fd88f8dac7a73745110545b83fc --- /dev/null +++ b/model-00033-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ce0f4dee522e265dd9c3a9557f6813fbe5a2dd68c790a686e51dd8bf5b545c +size 4994465872 diff --git a/model-00034-of-00043.safetensors b/model-00034-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dab0c68915894f561c5c9bd82bb89fa29befdde7 --- /dev/null +++ b/model-00034-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305d687bb88a1086a2f40fd31be0554349fe98ba72eb8ce10eb9912c802cb9d9 +size 4994465880 diff --git a/model-00035-of-00043.safetensors b/model-00035-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f80c8e72bab92949d52be8ad3785567ccfec2992 --- /dev/null +++ b/model-00035-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e300cc912ac8afc8d61322cda7cb83b03e496703a875b513448212e33f2a356 +size 4994465880 diff --git a/model-00036-of-00043.safetensors b/model-00036-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d89113d91b42cd43f9f70e830fb2efc3dad0ca64 --- /dev/null +++ b/model-00036-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa960d6a0239d981fb4b9cb7cd5dd937486ff2c96a2d4f900f32e24c2346a8c +size 4903255872 diff --git a/model-00037-of-00043.safetensors b/model-00037-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..596ed399518f0db894bb4c9eaa4c2f6f1e927ee4 --- /dev/null +++ b/model-00037-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:698c1848517f71752df5b55106b042682adbc08f5713700a81d38d6f04a875cc +size 4993444376 diff --git a/model-00038-of-00043.safetensors b/model-00038-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc0c94730e59282eb9c8503de97696d51516a53c --- /dev/null +++ b/model-00038-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca9698e6d8c9d7d6693618b3cce7109a531e4017710cecccedb8e7efd3087ebe +size 4994465840 diff --git a/model-00039-of-00043.safetensors b/model-00039-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bc0f0599b497fe54971cfb16c64e5a8958a359f --- /dev/null +++ b/model-00039-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3999a639dd7eb01c08e84b1d36a2cd48fb11ff81554ffe1af286c6eb57a41001 +size 4994465856 diff --git a/model-00040-of-00043.safetensors b/model-00040-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e439d49c1d7e23b185b42c7c860552e19f18ca85 --- /dev/null +++ b/model-00040-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924065b39beec0d5de82b1c86f63e8ce3ea2c7cd658ab08b5c7ee1bac6680926 +size 4994465856 diff --git a/model-00041-of-00043.safetensors b/model-00041-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8424b6e18cff775a4e5771fa93967c6ec21d8ea8 --- /dev/null +++ b/model-00041-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd8cabda80a11bb8ce209e9b8581f53c149bfa66b4b90aabaa9dc20252dc78a6 +size 4994465856 diff --git a/model-00042-of-00043.safetensors b/model-00042-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b742760a21520f540edd2520818d16a8692aa55c --- /dev/null +++ b/model-00042-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ea3efbee2727d6b2619e619d6bce7b3590dadd5e523488bf0d6a178bcb28eb +size 4994465856 diff --git a/model-00043-of-00043.safetensors b/model-00043-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d564ed9c164efb1c0cd8263a9c87879e5d324b6 --- /dev/null +++ b/model-00043-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eddc2e6b0ab9621e6f7505483ad68604f39db8fb17675e78b018526278551de3 +size 4056996736 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..67d1db98d6c8286e3caa9eb7847d5219553c8165 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,17933 @@ +{ + "metadata": { + "total_parameters": 106852245504, + "total_size": 213704502528 + }, + "weight_map": { + "lm_head.weight": "model-00043-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-00002-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-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00002-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-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00002-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-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00002-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-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00001-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-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-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-00001-of-00043.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.10.input_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.gate.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.11.input_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.gate.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.12.input_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.gate.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.13.input_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.gate.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.14.input_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.gate.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.15.input_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.gate.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.16.input_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.gate.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.17.input_layernorm.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.gate.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00017-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.18.input_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.gate.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.19.input_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.gate.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.20.input_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.gate.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.21.input_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.gate.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.22.input_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.gate.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.23.input_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.gate.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.input_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.gate.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.25.input_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.gate.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.26.input_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.gate.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.27.input_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.gate.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.28.input_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.gate.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.29.input_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.gate.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.30.input_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.gate.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.31.input_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.gate.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.32.input_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.gate.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.33.input_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.gate.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.34.input_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.gate.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.35.input_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.gate.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.36.input_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.gate.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.37.input_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.gate.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.38.input_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.gate.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.39.input_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.gate.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.40.input_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.gate.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.41.input_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.gate.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.42.input_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.gate.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.43.input_layernorm.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.gate.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00041-of-00043.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.44.input_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.gate.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.45.input_layernorm.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.gate.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00043-of-00043.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.6.input_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.gate.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.gate.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.gate.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.gate.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00043.safetensors", + "model.norm.weight": "model-00043-of-00043.safetensors" + } +} 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..de605bcb849be4351aa397f3e8b3fbf05b8fb666 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,326 @@ +{ + "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, + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}