diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..55b0d739e43abe9b990c0f261433e64684a39b06 --- /dev/null +++ b/README.md @@ -0,0 +1,39 @@ +--- +language: +- en +- zh +library_name: mlx +license: mit +pipeline_tag: text-generation +tags: +- mlx +base_model: zai-org/GLM-4.7 +--- + +# mlx-community/GLM-4.7-6bit + +This model [mlx-community/GLM-4.7-6bit](https://huggingface.co/mlx-community/GLM-4.7-6bit) was +converted to MLX format from [zai-org/GLM-4.7](https://huggingface.co/zai-org/GLM-4.7) +using mlx-lm version **0.30.0**. + +## Use with mlx + +```bash +pip install mlx-lm +``` + +```python +from mlx_lm import load, generate + +model, tokenizer = load("mlx-community/GLM-4.7-6bit") + +prompt = "hello" + +if tokenizer.chat_template is not None: + messages = [{"role": "user", "content": prompt}] + prompt = tokenizer.apply_chat_template( + messages, add_generation_prompt=True, return_dict=False, + ) + +response = generate(model, tokenizer, prompt=prompt, verbose=True) +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..2ab98ef068d62829d17c5ade1827b9f013fa2bbf --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,86 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name}{arg-key-1}{arg-value-1}{arg-key-2}{arg-value-2}...{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%} +{{ '' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '' }} +{%- endif -%} +{%- if content.strip() -%} +{{ content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{- '' + tc.name -}} +{% set _args = tc.arguments %}{% for k, v in _args.items() %}{{ k }}{{ v | tojson(ensure_ascii=False) if v is not string else v }}{% endfor %}{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '' }} +{{- m.content }} +{{- '' }} +{%- else -%} +<|observation|>{% for tr in m.content %} +{{ tr.output if tr.output is defined else tr }}{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|>{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4deb71e07197d85dca751135bbdf2a96cffcd3be --- /dev/null +++ b/config.json @@ -0,0 +1,53 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 3, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 202752, + "model_type": "glm4_moe", + "moe_intermediate_size": 1536, + "n_group": 1, + "n_routed_experts": 160, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 92, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "quantization": { + "group_size": 64, + "bits": 6, + "mode": "affine" + }, + "quantization_config": { + "group_size": 64, + "bits": 6, + "mode": "affine" + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 2.5, + "tie_word_embeddings": false, + "topk_group": 1, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.0", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f51194759eb31dde6fbc75a28e3fb7036f68161a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "temperature": 1.0, + "transformers_version": "4.56.2" +} diff --git a/model-00002-of-00054.safetensors b/model-00002-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0433b4637026fc0c18d1e24f6b0b8e9be13c6fd --- /dev/null +++ b/model-00002-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16cff14342a73215785386f084bcfea05096744249d93c67f2603449bf934038 +size 5243427265 diff --git a/model-00003-of-00054.safetensors b/model-00003-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d008ccb87bd7524a103d5c9ac82fbddbceda6b5 --- /dev/null +++ b/model-00003-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d13e3f9907858575e78755c026dc45f14056b9ebe336deee7ca6bf83930cc1 +size 5335722898 diff --git a/model-00004-of-00054.safetensors b/model-00004-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e414c1dadc43e6be052f409e6f9599986679cef --- /dev/null +++ b/model-00004-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8d3d3bec55a85884f05ddfd2dd187eabfb74eaf8ea9542b72396dbe0d151df +size 5363247106 diff --git a/model-00006-of-00054.safetensors b/model-00006-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b13310cab719cf0920b79c1f291e95c75bcdd410 --- /dev/null +++ b/model-00006-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef338aaa8cf218d5f648115bf1204f815fa2c6c88f40f55eb438ea0e6d8b1ecc +size 5335722946 diff --git a/model-00007-of-00054.safetensors b/model-00007-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..62eefc0ee4cb2f604bc1ef321722028468305c6f --- /dev/null +++ b/model-00007-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd587719b9421c932c73c5e263f4579ccb05a5a7e3a91e21b4d52e25340974c +size 5363247185 diff --git a/model-00008-of-00054.safetensors b/model-00008-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23a7adfe3d75b190631dc43390274cc55b1af688 --- /dev/null +++ b/model-00008-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3498245aa6744b6d64566441ab494607093fdeb6d0fe51fb74a7025dafd928c5 +size 5294546451 diff --git a/model-00009-of-00054.safetensors b/model-00009-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67d5cc29d29223fc9e681e9c9645e9d5c0bca354 --- /dev/null +++ b/model-00009-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fda13d3e57c622e9ac35327a53f984a66a1219e2c57a00bff2f33c72742d5a +size 5335722966 diff --git a/model-00010-of-00054.safetensors b/model-00010-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2783d96ea48b4b5723934e3d6bab061b7fd12418 --- /dev/null +++ b/model-00010-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b482d3aa9eeff6f0d2c86e7793efec28dd51dfeac9248a99cbe29191cbc7014f +size 5363247163 diff --git a/model-00011-of-00054.safetensors b/model-00011-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca226fb4d2a756aa24280533e3dea68a67bef722 --- /dev/null +++ b/model-00011-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ebad2f19c928199551d31a2d36a1ddd184f360fc18391817dc33d4cc8543f0d +size 5294546461 diff --git a/model-00012-of-00054.safetensors b/model-00012-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7dfb2af7675507897f393231745c75d2c6ccbfd3 --- /dev/null +++ b/model-00012-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5263fe261d802099517e827a0f869e9149708259d32068a454cd19814992d5 +size 5335722940 diff --git a/model-00013-of-00054.safetensors b/model-00013-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15d2e07872ad4547a3c66eb0159bda432a6511fd --- /dev/null +++ b/model-00013-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91be41def32e80c28abc041dc02b1005b998b31fc60897530a5f6fa4e69d6f79 +size 5363247197 diff --git a/model-00014-of-00054.safetensors b/model-00014-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4e7c3885af73a7b7ef88429967eb0502e5db0f3 --- /dev/null +++ b/model-00014-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07544e0672e33e61b199ef8e9bd450330da0b5ea6641573bcab391c8e8364767 +size 5294546487 diff --git a/model-00015-of-00054.safetensors b/model-00015-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d71aeed9004615b28dd2872ff3f3a7d6d70ed95 --- /dev/null +++ b/model-00015-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b207ad4820e6ccce1b27dc7a9ac48f7953c61e9726b80478db88286693cbb8 +size 5335722976 diff --git a/model-00016-of-00054.safetensors b/model-00016-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af1c4cd2264f9235c8032ee8f4d6d2fb642b8dde --- /dev/null +++ b/model-00016-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6269884e26c7ddb76faeeb7915c5ed07add2995cff66417565d5cc691136779 +size 5363247143 diff --git a/model-00017-of-00054.safetensors b/model-00017-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f650442b149916083f0f27600a3e4f03cd68c81 --- /dev/null +++ b/model-00017-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c9239ab6dc19e61db7b26fe2a48b6b874fda236a6cae7cee55b3a101b0a86d +size 5294546487 diff --git a/model-00018-of-00054.safetensors b/model-00018-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0f6cd49dbd9352598653638feed928b8332db5e --- /dev/null +++ b/model-00018-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53abbfadd78f8e5c52df1a446ebb9674efde733144b4a69f113dd2f869a03f2 +size 5335722962 diff --git a/model-00019-of-00054.safetensors b/model-00019-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c8d66d82f40b6642aca31186f843b93cca5197c --- /dev/null +++ b/model-00019-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de295008567e4fba618215efe94f0fb0a6d9f819d3b1bf8a7657d1728bebc048 +size 5363247181 diff --git a/model-00020-of-00054.safetensors b/model-00020-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78df65b761723ee7ca1921ee743dd9e3a0876f71 --- /dev/null +++ b/model-00020-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc18e2be69114e24e504c9f065eb90af1bc74cc1cdd738920284567b94bb3397 +size 5294546489 diff --git a/model-00021-of-00054.safetensors b/model-00021-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2d10217dbca4da78e874bc0f1b74605efcf2385 --- /dev/null +++ b/model-00021-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de19d6903d8e89d40a4abd46de45e6ceb04f0f0609f2fbc7916f68b12090401 +size 5335722984 diff --git a/model-00022-of-00054.safetensors b/model-00022-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7463225754a9c1343439bfe34126d7c37a5076a --- /dev/null +++ b/model-00022-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77f10ce0bfea2c0d734884cdfccb96b3a04b8e9e043b5617a191f368fd6afcf +size 5363247173 diff --git a/model-00023-of-00054.safetensors b/model-00023-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c2605d868fdbf30c487378590654a182addda2a --- /dev/null +++ b/model-00023-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40959bfaaca793f4f46f39193f0e1f1b39643a7c1c5619398629cb77b0b4ab3a +size 5294546481 diff --git a/model-00024-of-00054.safetensors b/model-00024-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf67f69d99f6bd58c07516205ea5e41a1ed4dbc0 --- /dev/null +++ b/model-00024-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5bb4fd1adbe38762b98583c2d1eeb60652443317098a70d5d2ee6545faba71 +size 5335722908 diff --git a/model-00026-of-00054.safetensors b/model-00026-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca50ff9e5cd47d3b50d449d4470ad1722326ee2e --- /dev/null +++ b/model-00026-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea07b8d473026f03da3e9301d863f192fb311d1de2c9dba342aa3058a5721e1 +size 5294546487 diff --git a/model-00027-of-00054.safetensors b/model-00027-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56f292f3e2138ea47a174fe0ce166d1e7b3649ac --- /dev/null +++ b/model-00027-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f82a8aaa511a46c3d3f5658a15ea72a3fe2a6965913f6a7d94229610f736bc6 +size 5335722916 diff --git a/model-00028-of-00054.safetensors b/model-00028-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46cf5449394484d8f79a58d6ed5fd7ed42b71547 --- /dev/null +++ b/model-00028-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e48cd5cbe62aaaf6f8b6422170b50d2b5b0cf3b70139cc56154337db350bc6 +size 5363247169 diff --git a/model-00029-of-00054.safetensors b/model-00029-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45cfbdcd1e1641f5b890aa0c6eff7c2a63628969 --- /dev/null +++ b/model-00029-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee55ba3fae6545f5a68e9ee6510178d4f599ceeb5a39943087374fedc639188 +size 5294546487 diff --git a/model-00030-of-00054.safetensors b/model-00030-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7fdc43e92fdd81c8042b85b1d258a4b3302cabb --- /dev/null +++ b/model-00030-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26798c517ea5ede4304cbd3064faf03611266a1830d7d2ea5e3eb0a95401bb0 +size 5335722970 diff --git a/model-00031-of-00054.safetensors b/model-00031-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..723e8421e1cfc192c9035b40d25d33550529931d --- /dev/null +++ b/model-00031-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f444a554f8ccd8ad7ea3e3df7b04c4f0dee7ecf350d467ef4767f5cc4d110719 +size 5363247195 diff --git a/model-00032-of-00054.safetensors b/model-00032-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7eebeafe9bdf964fcbf0bce08f105f53281b7f0a --- /dev/null +++ b/model-00032-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e3b5ea6f1cd53b160e204439fc429ab634969ead68ae76ce7ca21a5f2c1efb +size 5294546489 diff --git a/model-00034-of-00054.safetensors b/model-00034-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0a182122f35ba03d31f2e43651c6ba1600cf443 --- /dev/null +++ b/model-00034-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae0330166efef028d3ac3cf345154b4a390a62cbb4ffcaeea9128f97d3ccdea7 +size 5363247173 diff --git a/model-00035-of-00054.safetensors b/model-00035-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b5c32a4e5b19a818efc5a3492d80c0009c1922b --- /dev/null +++ b/model-00035-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fef0e8e8691d187731cd0afeb0ebb3036412e08f59220831d2075240b38e33e +size 5294546489 diff --git a/model-00038-of-00054.safetensors b/model-00038-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ae7bdb79cb03d863fe6ae11ad76f134a72ebd22 --- /dev/null +++ b/model-00038-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6355f5e524f07a32795e150eff92a0d55fa1210b43d7ac73c57b0337bc4b96ad +size 5294546491 diff --git a/model-00042-of-00054.safetensors b/model-00042-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d57152b7db8add7f97b87e05025b35de459a4d97 --- /dev/null +++ b/model-00042-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3399914f2a7c46ec67ab9bb4f6fb9cfd71463d7b5c07027b9ce1a1c21e16a4 +size 5335722966 diff --git a/model-00043-of-00054.safetensors b/model-00043-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f6332d43ee100b8ffd672d0a22b84642a61d21a --- /dev/null +++ b/model-00043-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80df53cbea6326c2f4a2005ecb958acd067baf5db63977aede74dbe257b3e1f1 +size 5363247181 diff --git a/model-00046-of-00054.safetensors b/model-00046-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c60401841934f308df22545abee3709617bc5cda --- /dev/null +++ b/model-00046-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a3626697d635fd2f2747d3a13dfd8bb608d5b5b39702050feefb5d1cacc9232 +size 5363247189 diff --git a/model-00047-of-00054.safetensors b/model-00047-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76f22530bcb1cc87757c91bfacc044bd9ccedba4 --- /dev/null +++ b/model-00047-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a8e1ff778ff3bd40d1a8602c8223ea4493f1176f21640c078e0e056ecb927d +size 5294546487 diff --git a/model-00048-of-00054.safetensors b/model-00048-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2cf308ecb674495cf60cae0b4c2f6c674178a873 --- /dev/null +++ b/model-00048-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a51694daa3cd400c0a92791f0fa6f7fdba0bd42387ce175f0c150d82520f5b0e +size 5335722980 diff --git a/model-00049-of-00054.safetensors b/model-00049-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a18ea4bc10d5bd0ade2ab3c4bb584852805e09fa --- /dev/null +++ b/model-00049-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e281c4dbce65d5be4e21738ca71937b6b6e6a4a8173e75c2b58bb9488c7d9d2 +size 5363247191 diff --git a/model-00050-of-00054.safetensors b/model-00050-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e35da335ab28194685abcb78136e148a05ef059 --- /dev/null +++ b/model-00050-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4da73ace5db626fd95107920d007f57c1c31f5b70b77fa761b762efcdd48ea5 +size 5294546489 diff --git a/model-00051-of-00054.safetensors b/model-00051-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53a07b1c8382ef34ce4e7f373736c290ca0d221b --- /dev/null +++ b/model-00051-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d3fad814de524e893eb81ace86f39cacfcc13bcd2cd9a8d75116df527dd0d8 +size 5335722964 diff --git a/model-00052-of-00054.safetensors b/model-00052-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55bbea93f913ffe684bb9e4fa6d1462500b140e2 --- /dev/null +++ b/model-00052-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3479ae96793c605bd438715f2f4d3731011f4df5e7492ea2f8e1a2e50fd333 +size 5363247191 diff --git a/model-00053-of-00054.safetensors b/model-00053-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23be8ba83563a4ba0fbb50b686bdbba64d2f9215 --- /dev/null +++ b/model-00053-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba2c0301e7c6fa8250e83273f6c847e833f1d2752c57263759b8a0246bf08de +size 5294546487 diff --git a/model-00054-of-00054.safetensors b/model-00054-of-00054.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47993dc8cdbabe612199918f490a9ae96b622d27 --- /dev/null +++ b/model-00054-of-00054.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f585ff4ee2be8d87975f1e74e9bc09275df220027924c23ea05ef69eef8e49c4 +size 4872362644 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e3c83201499eb9ea25e90dfe2fb1df03a8860d38 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3570 @@ +{ + "metadata": { + "total_size": 286737579648, + "total_parameters": 352797829024 + }, + "weight_map": { + "lm_head.biases": "model-00054-of-00054.safetensors", + "lm_head.scales": "model-00054-of-00054.safetensors", + "lm_head.weight": "model-00054-of-00054.safetensors", + "model.embed_tokens.biases": "model-00001-of-00054.safetensors", + "model.embed_tokens.scales": "model-00001-of-00054.safetensors", + "model.embed_tokens.weight": "model-00001-of-00054.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.10.input_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.gate.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.o_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.11.input_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.gate.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.o_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.input_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.gate.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.o_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.biases": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00006-of-00054.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00054.safetensors", + "model.layers.13.input_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.gate.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.o_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.14.input_layernorm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.gate.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.o_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.biases": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00007-of-00054.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00054.safetensors", + "model.layers.15.input_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.gate.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.o_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.biases": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00008-of-00054.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00054.safetensors", + "model.layers.16.input_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.gate.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.o_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.input_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.gate.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.o_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.biases": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00009-of-00054.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00054.safetensors", + "model.layers.18.input_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.gate.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.o_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.19.input_layernorm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.gate.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.o_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.biases": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00010-of-00054.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00054.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.20.input_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.gate.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.o_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.biases": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00011-of-00054.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00054.safetensors", + "model.layers.21.input_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.gate.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.o_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.input_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.gate.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.o_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.biases": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00012-of-00054.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00054.safetensors", + "model.layers.23.input_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.gate.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.o_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.24.input_layernorm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.gate.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.o_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.biases": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00013-of-00054.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00054.safetensors", + "model.layers.25.input_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.gate.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.o_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.biases": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00014-of-00054.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00054.safetensors", + "model.layers.26.input_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.gate.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.o_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.input_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.gate.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.o_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.biases": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00015-of-00054.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00054.safetensors", + "model.layers.28.input_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.gate.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.o_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.29.input_layernorm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.gate.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.o_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.biases": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00016-of-00054.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00054.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.gate.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.30.input_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.gate.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.o_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.biases": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00017-of-00054.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00054.safetensors", + "model.layers.31.input_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.gate.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.o_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.input_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.gate.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.o_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.biases": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00018-of-00054.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00054.safetensors", + "model.layers.33.input_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.gate.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.o_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.34.input_layernorm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.gate.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.o_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.biases": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00019-of-00054.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00054.safetensors", + "model.layers.35.input_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.gate.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.o_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.biases": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00020-of-00054.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00054.safetensors", + "model.layers.36.input_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.gate.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.o_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.input_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.gate.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.o_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.biases": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00021-of-00054.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00054.safetensors", + "model.layers.38.input_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.gate.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.o_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.39.input_layernorm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.gate.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.o_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.biases": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00022-of-00054.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00054.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.gate.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00054.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00054.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00054.safetensors", + "model.layers.40.input_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.gate.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.o_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.biases": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00023-of-00054.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00023-of-00054.safetensors", + "model.layers.41.input_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.gate.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.o_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.input_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.gate.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.o_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.biases": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00024-of-00054.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00024-of-00054.safetensors", + "model.layers.43.input_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.gate.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.o_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.44.input_layernorm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.gate.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.o_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.biases": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00025-of-00054.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00025-of-00054.safetensors", + "model.layers.45.input_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.gate.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.o_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.biases": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00026-of-00054.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00026-of-00054.safetensors", + "model.layers.46.input_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.gate.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.o_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.input_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.gate.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.o_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.biases": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00027-of-00054.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00027-of-00054.safetensors", + "model.layers.48.input_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.gate.e_score_correction_bias": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.gate.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.down_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.mlp.switch_mlp.up_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.o_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.49.input_layernorm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.gate.e_score_correction_bias": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.gate.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.down_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.mlp.switch_mlp.up_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.o_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.biases": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00028-of-00054.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00028-of-00054.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.gate.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.o_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.biases": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00002-of-00054.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00054.safetensors", + "model.layers.50.input_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.gate.e_score_correction_bias": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.gate.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.mlp.switch_mlp.up_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.o_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.biases": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00029-of-00054.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00054.safetensors", + "model.layers.51.input_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.gate.e_score_correction_bias": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.gate.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.down_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.mlp.switch_mlp.up_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.o_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.input_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.gate.e_score_correction_bias": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.gate.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.52.mlp.switch_mlp.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.o_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.biases": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00030-of-00054.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00030-of-00054.safetensors", + "model.layers.53.input_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.gate.e_score_correction_bias": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.gate.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.down_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.gate_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.mlp.switch_mlp.up_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.o_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.54.input_layernorm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.gate.e_score_correction_bias": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.gate.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.down_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.mlp.switch_mlp.up_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.o_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.biases": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00031-of-00054.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00031-of-00054.safetensors", + "model.layers.55.input_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.gate.e_score_correction_bias": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.gate.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.mlp.switch_mlp.up_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.o_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.biases": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00032-of-00054.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00054.safetensors", + "model.layers.56.input_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.gate.e_score_correction_bias": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.gate.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.down_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.mlp.switch_mlp.up_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.o_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.input_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.gate.e_score_correction_bias": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.gate.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.57.mlp.switch_mlp.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.o_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.biases": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00033-of-00054.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00054.safetensors", + "model.layers.58.input_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.gate.e_score_correction_bias": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.gate.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.down_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.gate_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.mlp.switch_mlp.up_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.o_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.59.input_layernorm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.gate.e_score_correction_bias": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.gate.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.down_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.mlp.switch_mlp.up_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.o_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.biases": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00034-of-00054.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00034-of-00054.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.gate.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.o_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.60.input_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.gate.e_score_correction_bias": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.gate.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.mlp.switch_mlp.up_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.o_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.o_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.biases": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.scales": "model-00035-of-00054.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00054.safetensors", + "model.layers.61.input_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.gate.e_score_correction_bias": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.gate.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.down_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.mlp.switch_mlp.up_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.o_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.o_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.input_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.gate.e_score_correction_bias": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.gate.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.62.mlp.switch_mlp.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.o_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.o_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.biases": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.scales": "model-00036-of-00054.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00036-of-00054.safetensors", + "model.layers.63.input_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.gate.e_score_correction_bias": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.gate.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.down_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.gate_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.mlp.switch_mlp.up_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.o_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.o_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.64.input_layernorm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.gate.e_score_correction_bias": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.gate.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.down_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.gate_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.mlp.switch_mlp.up_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.k_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.o_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.o_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.q_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.bias": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.biases": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.scales": "model-00037-of-00054.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00037-of-00054.safetensors", + "model.layers.65.input_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.gate.e_score_correction_bias": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.gate.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.gate_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.mlp.switch_mlp.up_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.65.self_attn.k_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.bias": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.o_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.o_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_norm.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.bias": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.bias": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.biases": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.scales": "model-00038-of-00054.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00038-of-00054.safetensors", + "model.layers.66.input_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.gate.e_score_correction_bias": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.gate.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.down_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.mlp.switch_mlp.up_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.o_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.o_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.input_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.gate.e_score_correction_bias": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.gate.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.gate_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.67.mlp.switch_mlp.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.67.self_attn.k_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.o_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.o_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_norm.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.bias": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.biases": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.scales": "model-00039-of-00054.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00039-of-00054.safetensors", + "model.layers.68.input_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.gate.e_score_correction_bias": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.gate.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.down_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.gate_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.mlp.switch_mlp.up_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_norm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.o_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.o_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_norm.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.69.input_layernorm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.gate.e_score_correction_bias": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.gate.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.down_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.gate_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.mlp.switch_mlp.up_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.k_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.o_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.o_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.q_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.bias": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.biases": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.scales": "model-00040-of-00054.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00040-of-00054.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.gate.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.o_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.biases": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00003-of-00054.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00054.safetensors", + "model.layers.70.input_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.gate.e_score_correction_bias": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.gate.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.gate_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.mlp.switch_mlp.up_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.70.self_attn.k_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.bias": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.o_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.o_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_norm.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.bias": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.bias": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.biases": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.scales": "model-00041-of-00054.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00041-of-00054.safetensors", + "model.layers.71.input_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.gate.e_score_correction_bias": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.gate.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.down_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.mlp.switch_mlp.up_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.o_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.o_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.input_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.gate.e_score_correction_bias": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.gate.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.gate_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.72.mlp.switch_mlp.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.72.self_attn.k_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.o_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.o_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_norm.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.bias": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.biases": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.scales": "model-00042-of-00054.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00042-of-00054.safetensors", + "model.layers.73.input_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.gate.e_score_correction_bias": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.gate.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.down_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.gate_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.mlp.switch_mlp.up_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_norm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.o_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.o_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_norm.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.74.input_layernorm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.gate.e_score_correction_bias": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.gate.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.down_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.gate_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.mlp.switch_mlp.up_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.k_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.o_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.o_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.q_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.bias": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.biases": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.scales": "model-00043-of-00054.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00043-of-00054.safetensors", + "model.layers.75.input_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.gate.e_score_correction_bias": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.gate.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.gate_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.mlp.switch_mlp.up_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.75.self_attn.k_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.bias": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.o_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.o_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_norm.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.bias": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.bias": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.biases": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.scales": "model-00044-of-00054.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00044-of-00054.safetensors", + "model.layers.76.input_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.gate.e_score_correction_bias": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.gate.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.down_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.mlp.switch_mlp.up_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.o_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.o_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.input_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.gate.e_score_correction_bias": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.gate.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.gate_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.77.mlp.switch_mlp.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.77.self_attn.k_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.o_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.o_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_norm.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.bias": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.biases": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.scales": "model-00045-of-00054.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00045-of-00054.safetensors", + "model.layers.78.input_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.gate.e_score_correction_bias": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.gate.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.down_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.gate_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.mlp.switch_mlp.up_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_norm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.o_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.o_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_norm.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.79.input_layernorm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.gate.e_score_correction_bias": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.gate.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.down_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.gate_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.mlp.switch_mlp.up_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.k_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.o_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.o_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.q_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.bias": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.biases": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.scales": "model-00046-of-00054.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00046-of-00054.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.gate.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.o_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.80.input_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.gate.e_score_correction_bias": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.gate.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.gate_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.mlp.switch_mlp.up_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.80.self_attn.k_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.bias": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.o_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.o_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_norm.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.bias": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.bias": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.biases": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.scales": "model-00047-of-00054.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00047-of-00054.safetensors", + "model.layers.81.input_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.gate.e_score_correction_bias": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.gate.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.down_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.mlp.switch_mlp.up_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.o_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.o_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.input_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.gate.e_score_correction_bias": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.gate.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.gate_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.82.mlp.switch_mlp.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.82.self_attn.k_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.o_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.o_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_norm.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.bias": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.biases": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.scales": "model-00048-of-00054.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00048-of-00054.safetensors", + "model.layers.83.input_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.gate.e_score_correction_bias": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.gate.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.down_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.gate_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.mlp.switch_mlp.up_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_norm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.o_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.o_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_norm.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.84.input_layernorm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.gate.e_score_correction_bias": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.gate.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.down_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.gate_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.mlp.switch_mlp.up_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.k_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.o_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.o_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.q_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.bias": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.biases": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.scales": "model-00049-of-00054.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00049-of-00054.safetensors", + "model.layers.85.input_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.gate.e_score_correction_bias": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.gate.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.gate_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.mlp.switch_mlp.up_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.85.self_attn.k_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.bias": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.o_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.o_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_norm.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.bias": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.bias": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.biases": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.scales": "model-00050-of-00054.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00050-of-00054.safetensors", + "model.layers.86.input_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.gate.e_score_correction_bias": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.gate.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.down_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.mlp.switch_mlp.up_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.o_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.o_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.input_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.gate.e_score_correction_bias": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.gate.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.gate_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.87.mlp.switch_mlp.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.87.self_attn.k_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.o_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.o_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_norm.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.bias": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.biases": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.scales": "model-00051-of-00054.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00051-of-00054.safetensors", + "model.layers.88.input_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.gate.e_score_correction_bias": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.gate.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.down_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.gate_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.mlp.switch_mlp.up_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_norm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.o_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.o_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_norm.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.89.input_layernorm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.gate.e_score_correction_bias": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.gate.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.down_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.gate_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.mlp.switch_mlp.up_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.k_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.o_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.o_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.q_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.bias": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.biases": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.scales": "model-00052-of-00054.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00052-of-00054.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.gate.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.o_proj.biases": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.biases": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00004-of-00054.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00054.safetensors", + "model.layers.90.input_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.gate.e_score_correction_bias": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.gate.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.gate_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.mlp.switch_mlp.up_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.90.self_attn.k_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.bias": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.o_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.o_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_norm.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.bias": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.bias": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.biases": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.scales": "model-00053-of-00054.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00053-of-00054.safetensors", + "model.layers.91.input_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.gate.e_score_correction_bias": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.gate.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.down_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.gate_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.mlp.switch_mlp.up_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_norm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.bias": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.o_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.o_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_norm.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.bias": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.bias": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.biases": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.scales": "model-00054-of-00054.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00054-of-00054.safetensors", + "model.norm.weight": "model-00054-of-00054.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..2f90e1190a0ea9ebdf15676b13617b3d7c222d28 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ccf2252fe9cd23ada23a829ec409aab397dbd2ac4f372d3a1a23d1f7c72d6b +size 19970686 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1c5a4bdfec2c8806a58658accd0e13af019b082d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,61 @@ +{ + "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" + ], + "backend": "tokenizers", + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "is_local": true, + "model_max_length": 128000, + "model_specific_special_tokens": {}, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "TokenizersBackend" +}