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..a022801f790dc00be27d03cc1b7fd1ca7af67b93 --- /dev/null +++ b/README.md @@ -0,0 +1,168 @@ +--- +tags: +- unsloth +base_model: +- zai-org/GLM-4.7-Flash +language: + - en + - zh +library_name: transformers +license: mit +pipeline_tag: text-generation +--- +> [!NOTE] +> Includes Unsloth **chat template fixes**!
For `llama.cpp`, use `--jinja` +> + +
+

+ Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. +

+
+ + + + + + + + + +
+
+ + +# GLM-4.7-Flash + +
+ +
+

+ 👋 Join our Discord community. +
+ 📖 Check out the GLM-4.7 technical blog, technical report(GLM-4.5). +
+ 📍 Use GLM-4.7-Flash API services on Z.ai API Platform. +
+ 👉 One click to GLM-4.7. +

+ +## Introduction + +GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency. + + +### Performances on Benchmarks + + +| Benchmark | GLM-4.7-Flash | Qwen3-30B-A3B-Thinking-2507 | GPT-OSS-20B | +|--------------------|---------------|-----------------------------|-------------| +| AIME 25 | 91.6 | 85.0 | 91.7 | +| GPQA | 75.2 | 73.4 | 71.5 | +| LCB v6 | 64.0 | 66.0 | 61.0 | +| HLE | 14.4 | 9.8 | 10.9 | +| SWE-bench Verified | 59.2 | 22.0 | 34.0 | +| τ²-Bench | 79.5 | 49.0 | 47.7 | +| BrowseComp | 42.8 | 2.29 | 28.3 | + + +## Serve GLM-4.7-Flash Locally + +For local deployment, GLM-4.7-Flash supports inference frameworks including vLLM and SGLang. Comprehensive deployment +instructions are available in the official [Github](https://github.com/zai-org/GLM-4.5) repository. + +vLLM and SGLang only support GLM-4.7-Flash on their main branches. + +### vLLM + ++ using pip (must use pypi.org as the index url): + +```shell +pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly +pip install git+https://github.com/huggingface/transformers.git +``` + +### SGLang + ++ using pip install sglang from source, then update transformers to the latest main branch. + +### transformers + +using with transformers as + +```shell +pip install git+https://github.com/huggingface/transformers.git +``` + +and then run: + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +MODEL_PATH = "zai-org/GLM-4.7-Flash" +messages = [{"role": "user", "content": "hello"}] +tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH) +inputs = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_dict=True, + return_tensors="pt", +) +model = AutoModelForCausalLM.from_pretrained( + pretrained_model_name_or_path=MODEL_PATH, + torch_dtype=torch.bfloat16, + device_map="auto", +) +inputs = inputs.to(model.device) +generated_ids = model.generate(**inputs, max_new_tokens=128, do_sample=False) +output_text = tokenizer.decode(generated_ids[0][inputs.input_ids.shape[1]:]) +print(output_text) +``` + +### vLLM + +```shell +vllm serve zai-org/GLM-4.7-Flash \ + --tensor-parallel-size 4 \ + --speculative-config.method mtp \ + --speculative-config.num_speculative_tokens 1 \ + --tool-call-parser glm47 \ + --reasoning-parser glm45 \ + --enable-auto-tool-choice \ + --served-model-name glm-4.7-flash +``` + +### SGLang + +```shell +python3 -m sglang.launch_server \ + --model-path zai-org/GLM-4.7-Flash \ + --tp-size 4 \ + --tool-call-parser glm47 \ + --reasoning-parser glm45 \ + --speculative-algorithm EAGLE \ + --speculative-num-steps 3 \ + --speculative-eagle-topk 1 \ + --speculative-num-draft-tokens 4 \ + --mem-fraction-static 0.8 \ + --served-model-name glm-4.7-flash \ + --host 0.0.0.0 \ + --port 8000 +``` + +## Citation + +If you find our work useful in your research, please consider citing the following paper: + +```bibtex +@misc{5team2025glm45agenticreasoningcoding, + title={GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models}, + author={GLM Team and Aohan Zeng and Xin Lv and Qinkai Zheng and Zhenyu Hou and Bin Chen and Chengxing Xie and Cunxiang Wang and Da Yin and Hao Zeng and Jiajie Zhang and Kedong Wang and Lucen Zhong and Mingdao Liu and Rui Lu and Shulin Cao and Xiaohan Zhang and Xuancheng Huang and Yao Wei and Yean Cheng and Yifan An and Yilin Niu and Yuanhao Wen and Yushi Bai and Zhengxiao Du and Zihan Wang and Zilin Zhu and Bohan Zhang and Bosi Wen and Bowen Wu and Bowen Xu and Can Huang and Casey Zhao and Changpeng Cai and Chao Yu and Chen Li and Chendi Ge and Chenghua Huang and Chenhui Zhang and Chenxi Xu and Chenzheng Zhu and Chuang Li and Congfeng Yin and Daoyan Lin and Dayong Yang and Dazhi Jiang and Ding Ai and Erle Zhu and Fei Wang and Gengzheng Pan and Guo Wang and Hailong Sun and Haitao Li and Haiyang Li and Haiyi Hu and Hanyu Zhang and Hao Peng and Hao Tai and Haoke Zhang and Haoran Wang and Haoyu Yang and He Liu and He Zhao and Hongwei Liu and Hongxi Yan and Huan Liu and Huilong Chen and Ji Li and Jiajing Zhao and Jiamin Ren and Jian Jiao and Jiani Zhao and Jianyang Yan and Jiaqi Wang and Jiayi Gui and Jiayue Zhao and Jie Liu and Jijie Li and Jing Li and Jing Lu and Jingsen Wang and Jingwei Yuan and Jingxuan Li and Jingzhao Du and Jinhua Du and Jinxin Liu and Junkai Zhi and Junli Gao and Ke Wang and Lekang Yang and Liang Xu and Lin Fan and Lindong Wu and Lintao Ding and Lu Wang and Man Zhang and Minghao Li and Minghuan Xu and Mingming Zhao and Mingshu Zhai and Pengfan Du and Qian Dong and Shangde Lei and Shangqing Tu and Shangtong Yang and Shaoyou Lu and Shijie Li and Shuang Li and Shuang-Li and Shuxun Yang and Sibo Yi and Tianshu Yu and Wei Tian and Weihan Wang and Wenbo Yu and Weng Lam Tam and Wenjie Liang and Wentao Liu and Xiao Wang and Xiaohan Jia and Xiaotao Gu and Xiaoying Ling and Xin Wang and Xing Fan and Xingru Pan and Xinyuan Zhang and Xinze Zhang and Xiuqing Fu and Xunkai Zhang and Yabo Xu and Yandong Wu and Yida Lu and Yidong Wang and Yilin Zhou and Yiming Pan and Ying Zhang and Yingli Wang and Yingru Li and Yinpei Su and Yipeng Geng and Yitong Zhu and Yongkun Yang and Yuhang Li and Yuhao Wu and Yujiang Li and Yunan Liu and Yunqing Wang and Yuntao Li and Yuxuan Zhang and Zezhen Liu and Zhen Yang and Zhengda Zhou and Zhongpei Qiao and Zhuoer Feng and Zhuorui Liu and Zichen Zhang and Zihan Wang and Zijun Yao and Zikang Wang and Ziqiang Liu and Ziwei Chai and Zixuan Li and Zuodong Zhao and Wenguang Chen and Jidong Zhai and Bin Xu and Minlie Huang and Hongning Wang and Juanzi Li and Yuxiao Dong and Jie Tang}, + year={2025}, + eprint={2508.06471}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2508.06471}, +} \ No newline at end of file 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..43cfac7c427e8b6e11c275fe7fb3f67388809026 --- /dev/null +++ b/config.json @@ -0,0 +1,45 @@ +{ + "architectures": [ + "Glm4MoeLiteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "pad_token_id": 154820, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "hidden_act": "silu", + "hidden_size": 2048, + "intermediate_size": 10240, + "max_position_embeddings": 202752, + "model_type": "glm4_moe_lite", + "moe_intermediate_size": 1536, + "topk_method": "noaux_tc", + "norm_topk_prob": true, + "num_attention_heads": 20, + "n_group": 1, + "topk_group": 1, + "n_routed_experts": 64, + "n_shared_experts": 1, + "routed_scaling_factor": 1.8, + "num_experts_per_tok": 4, + "first_k_dense_replace": 1, + "num_hidden_layers": 47, + "num_key_value_heads": 20, + "num_nextn_predict_layers": 1, + "partial_rotary_factor": 1.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "5.0.0rc0", + "q_lora_rank": 768, + "kv_lora_rank": 512, + "qk_nope_head_dim": 192, + "qk_rope_head_dim": 64, + "v_head_dim": 256, + "vocab_size": 154880 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1dfa4cbf88115f19b4c6fcb086cc5669d2ce5e57 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "pad_token_id": 154820, + "temperature": 1.0, + "transformers_version": "5.0.0.dev0" +} diff --git a/model-00001-of-00048.safetensors b/model-00001-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79555e094b687b0c0a756194a914b9cfba4fb845 --- /dev/null +++ b/model-00001-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90abe0d075755853145c96906a1300f57c167fcc9aa67221239b448abf54933c +size 1438134344 diff --git a/model-00002-of-00048.safetensors b/model-00002-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..997031ad328ea332bafdcc1ed60aac02048262a7 --- /dev/null +++ b/model-00002-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c51e2434efe609cbe652014a924e088a5ea97be35ca29cfa893a1a9a90304b1 +size 1270648128 diff --git a/model-00003-of-00048.safetensors b/model-00003-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b40174d31d358efd9127a5b31c4a4b00ad1f803b --- /dev/null +++ b/model-00003-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab6ebdd01af10c9bde1ec0b2a182d6f7ff8df831add6810695e5f3b50918040d +size 1270648128 diff --git a/model-00004-of-00048.safetensors b/model-00004-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b0a6619cf5fc5a32776a4716f83daddc609376b --- /dev/null +++ b/model-00004-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932e4dbb8f7583d2b6392a6e850dd7aa05636827e8b90ff7858cae709838dca7 +size 1270648128 diff --git a/model-00005-of-00048.safetensors b/model-00005-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2da92dc95b670cf71495dd3cb16a6ecf523ec917 --- /dev/null +++ b/model-00005-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f56a3e52bf5905c2df07ef53575ae8e62622138a15b0affc2b3f84785ca81e9 +size 1270648128 diff --git a/model-00006-of-00048.safetensors b/model-00006-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6997f1fb888c80f04d317e02dfbb114c48d74e0e --- /dev/null +++ b/model-00006-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83aa0eeca6e5a9394bb8a1c9cab46cc603799d729cf64ed4bbc341e0a7085feb +size 1270648128 diff --git a/model-00007-of-00048.safetensors b/model-00007-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12e328dbc944dbfba15d7306817bf7f48bedc43e --- /dev/null +++ b/model-00007-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9679076d3bd10c5f1287d12418fddb41c8b54b8c8ccc0672796ef7e8431b797 +size 1270648128 diff --git a/model-00008-of-00048.safetensors b/model-00008-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58e42d5d15e86d7f4c8639e8964b505617bae692 --- /dev/null +++ b/model-00008-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d1231577a057ff957d480c277e497910acbba75fc9232f8fd8f44c1a647d7a2 +size 1270648128 diff --git a/model-00009-of-00048.safetensors b/model-00009-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fdcac5f154114b539d8be24032d93963a2c41d63 --- /dev/null +++ b/model-00009-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:095d626626773284535ba4114c2b320003ba3c8430bd104f5e7bba3772b2a1b1 +size 1270648128 diff --git a/model-00010-of-00048.safetensors b/model-00010-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1d2b7d3960a92e165d4c4dc1e458b774f5d71fe --- /dev/null +++ b/model-00010-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f8d197b0d253082f547d67989b1e3928a742b508f6f8d4abf119f3ba2990ed +size 1270648128 diff --git a/model-00011-of-00048.safetensors b/model-00011-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8ec965155a3249502752883b7a4a7694c7a308d --- /dev/null +++ b/model-00011-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b7eeef625a6ed9ced479e064870f0ebf0da67056cd5e582300d0ebcf44de21 +size 1270648328 diff --git a/model-00012-of-00048.safetensors b/model-00012-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb8413120307cacac10adee29fb1a9636e9274f0 --- /dev/null +++ b/model-00012-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49adb8b9f02d1643ab22406b0e05938ce3d7a8986fd0981e0af5d4cd47ee8b12 +size 1270648328 diff --git a/model-00013-of-00048.safetensors b/model-00013-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17e8b0917cb7dda545724eba28e17b50f4fbe3bc --- /dev/null +++ b/model-00013-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f269382ae6ce42cd05937fcd5551e08da151c810a87bb0e1994ff9bb5f9eb7c9 +size 1270648328 diff --git a/model-00014-of-00048.safetensors b/model-00014-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab153463bacfdcb5a838eb983f0da983c9ece15a --- /dev/null +++ b/model-00014-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd6f36aadceda658a5db6fc6a04160ae2ca1ae78d4a9c84aeabcea8e80b44c8 +size 1270648328 diff --git a/model-00015-of-00048.safetensors b/model-00015-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2411b85d38cad605c45d391beccb8b1aaee7c018 --- /dev/null +++ b/model-00015-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606079fe1e000d658142c59fee66aa8d7c949d758612debd78d21cde2fae392c +size 1270648328 diff --git a/model-00016-of-00048.safetensors b/model-00016-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68962301a992f65ed0a1e9c9e1bf4ab54d7a95cf --- /dev/null +++ b/model-00016-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53fb45f7689b505fc185180503ea9d45af67042ba38914e53bbdee97173c974 +size 1270648328 diff --git a/model-00017-of-00048.safetensors b/model-00017-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01d6586877e539d465c460cd7d296c785b73e6db --- /dev/null +++ b/model-00017-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a51e478badd50bb9b5299e3ad7979bfd40da8ab96983de0cd16a0fb5fddb4bc9 +size 1270648328 diff --git a/model-00018-of-00048.safetensors b/model-00018-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68dc7197418765aba3b493ee4a281e1f0913bde6 --- /dev/null +++ b/model-00018-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:680295c83f29a90c97f2d68c1290a152330c2dbd3654abdf0f074e6d8018062c +size 1270648328 diff --git a/model-00019-of-00048.safetensors b/model-00019-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db04efb5a3c29dd02bad27cc8415e14c0ef00fb2 --- /dev/null +++ b/model-00019-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355f9437e291b0846b5ecac1d644766ec17bd4863da441e4e786f33d7bac3347 +size 1270648328 diff --git a/model-00020-of-00048.safetensors b/model-00020-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..baf9ea29efde5e248ec4c91786716c7590345a5e --- /dev/null +++ b/model-00020-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8d4698fc5ce834021254b407c61e5376a693dcafeb996a8fc708639b44aed8 +size 1270648328 diff --git a/model-00021-of-00048.safetensors b/model-00021-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..335e00c78b3cce10bfecc2f3232e345cba372c79 --- /dev/null +++ b/model-00021-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111570fc7f55bcb9beb7bcb969475b27ffbcad97b95788464ff91a1e07ff897a +size 1270648328 diff --git a/model-00022-of-00048.safetensors b/model-00022-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07a061e0e0934142427191ad333c4faf730e2b75 --- /dev/null +++ b/model-00022-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced6a73df393df3bd559fc69093763fb5cc9fedee31e245a52a7786939199896 +size 1270648328 diff --git a/model-00023-of-00048.safetensors b/model-00023-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58373c6654392c0421fd30fdd8634382f2274c07 --- /dev/null +++ b/model-00023-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b287bb0ce12a1ac975978c94548f2bbab3267e83e0c888871a3ada3ddf91405d +size 1270648328 diff --git a/model-00024-of-00048.safetensors b/model-00024-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c589464afa8126aa1ec30956b336b15a3a6114f5 --- /dev/null +++ b/model-00024-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e77476f0f57dc0386b64741d9251632d46e646faab6780d10a5a6a5f456668 +size 1270648328 diff --git a/model-00025-of-00048.safetensors b/model-00025-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90e8b33614347252ba7b173d756e2f5d13728783 --- /dev/null +++ b/model-00025-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9e643d9d3e9152b9156424615c8054cffe6b8bc1b776567da17bbd3b97ebcb +size 1270648328 diff --git a/model-00026-of-00048.safetensors b/model-00026-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3a69ccd49e63f282bf44eb16afb22242cd89512 --- /dev/null +++ b/model-00026-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634da561277b9b77410a319bd930e940d443055fb688a2e4b9574aae1569192d +size 1270648328 diff --git a/model-00027-of-00048.safetensors b/model-00027-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..003975279dd3a8b514b3d16053cb38d33cb0776d --- /dev/null +++ b/model-00027-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3286537b5a5dd2b4742878476601a4f5b1f061e948386babe05076fd058fa5ec +size 1270648328 diff --git a/model-00028-of-00048.safetensors b/model-00028-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f7c1f3479dc27ce604078be87e564c00587fde4 --- /dev/null +++ b/model-00028-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56335c906d44c1c6f37530d65182cd6af4fb146fa8a68e8e510d6419b5b007e7 +size 1270648328 diff --git a/model-00029-of-00048.safetensors b/model-00029-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d28749af56eb5a710f183e00474cff20a35dde20 --- /dev/null +++ b/model-00029-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6591dfb36a59918f91c152ba0baf184b4372c667fe46f74024e5d8ae86f378 +size 1270648328 diff --git a/model-00030-of-00048.safetensors b/model-00030-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e8b0750abdab36aa3e0253755186c6c73126898 --- /dev/null +++ b/model-00030-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62373b800980841e6ca5c4c48db570729246092d03ac756bdeb55ecfdd599a2c +size 1270648328 diff --git a/model-00031-of-00048.safetensors b/model-00031-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..613b2e764dce2ad3203a225df42ad8b1d6932988 --- /dev/null +++ b/model-00031-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332d82cefb0b4d87c48e3e989c97d3e74b6f64326313694ed226a72bf26e3b99 +size 1270648328 diff --git a/model-00032-of-00048.safetensors b/model-00032-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ae2bca6bb87f5d388c8ce055dd591aacae6d23e --- /dev/null +++ b/model-00032-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9897915eef55f41b221ff072d8b0b401e447007d648b63ddabf9b795361c18 +size 1270648328 diff --git a/model-00033-of-00048.safetensors b/model-00033-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b508d7e86e41dbc3703c34dd95145665bbdb5122 --- /dev/null +++ b/model-00033-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29059fb79e6fefaad49b7c2833370cd78079b403cc98bc28ce95976207840f7f +size 1270648328 diff --git a/model-00034-of-00048.safetensors b/model-00034-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..423244000d188e4711e43f4d3ab25749185a352d --- /dev/null +++ b/model-00034-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f989cc8af19949a310599c5ab8d65f0ae8406908e1a702588b892604179061a1 +size 1270648328 diff --git a/model-00035-of-00048.safetensors b/model-00035-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bbcac89a658ea7146894bfa0ca8bacf02c4f78a --- /dev/null +++ b/model-00035-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa91e9b1a075d1753e45a01db198ed48f2739392e46e1843a4dcaaab6cd02eb +size 1270648328 diff --git a/model-00036-of-00048.safetensors b/model-00036-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80f58c4558afd475957bdd8a0f2f016f81988932 --- /dev/null +++ b/model-00036-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf807da31533424a54196cd07da6caa1a22199b72d822bd8c2f387172b6e1c65 +size 1270648328 diff --git a/model-00037-of-00048.safetensors b/model-00037-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e476c6267dab00b72896cacba5d99a237b5df0a --- /dev/null +++ b/model-00037-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887aeb5568ef6189a7618309e50f0277ad339da86133526ca6d820b88ecbb5d4 +size 1270648328 diff --git a/model-00038-of-00048.safetensors b/model-00038-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc7804c6900ab97ce51d7cd545204e4e4eb5d0a6 --- /dev/null +++ b/model-00038-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036a38cc10858a8cc5a2fcd09fdab1b53258d04ff87dc4d3d21f140c54b029dd +size 1270648328 diff --git a/model-00039-of-00048.safetensors b/model-00039-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24b4684c06c30707bfe4dbc93d7e452fa39ed46c --- /dev/null +++ b/model-00039-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ae341291fe720719ab6cdcf2348752f262f4575a3f8221b353deb224bcbd1d +size 1270648328 diff --git a/model-00040-of-00048.safetensors b/model-00040-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f12ecb438675ef82539b00d5cf9e3cb774e2d3bd --- /dev/null +++ b/model-00040-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8af33462a3f7b4dbc5393da4016acffabafc20b826f952e912adb2a2845fe3 +size 1270648328 diff --git a/model-00041-of-00048.safetensors b/model-00041-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2182f0a8f533f4a69d8ad77aea87fff3ebc0f335 --- /dev/null +++ b/model-00041-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39098c9b6770ff5c185a70b8f0d6cfca22f95e3c47dc38de88c3d2ec2b1cf5bc +size 1270648328 diff --git a/model-00042-of-00048.safetensors b/model-00042-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..379550a2efc703f67b9d19e2325b7c7b164154d4 --- /dev/null +++ b/model-00042-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe0b23aab19b608ca59f46628064c3d53d846c81d6f978c2579b38e09e35747 +size 1270648328 diff --git a/model-00043-of-00048.safetensors b/model-00043-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..976c35fdae9c1a22274f0f3005d01ad444ed4ba6 --- /dev/null +++ b/model-00043-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe1da68f8c30d7e77a68d48eb7d65d28709f536062dba8168490370cca47ba4 +size 1270648328 diff --git a/model-00044-of-00048.safetensors b/model-00044-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5b4ff5cff42a2bdde049511d5c84cc23c371363 --- /dev/null +++ b/model-00044-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a731baa1370864ad61cf8fe8000cb8e1e266529206824a3ce96b5229eb3c53c8 +size 1270648328 diff --git a/model-00045-of-00048.safetensors b/model-00045-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a898e8fd107eabeb2517ec1a7e192216903b534c --- /dev/null +++ b/model-00045-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a636f872a931396d2fdc57b6c715294e14b3c8040420ffce856a2a0a18194916 +size 1270648328 diff --git a/model-00046-of-00048.safetensors b/model-00046-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..801fa3f61579792d210ca77eb289b46ba63179d3 --- /dev/null +++ b/model-00046-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba5365e31c27cd13e330a7135f7251f3bf16e99c8504acffa9e8190b585eb773 +size 1270648328 diff --git a/model-00047-of-00048.safetensors b/model-00047-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8786bf839075106343818c3dcb69ebc6cb3af933 --- /dev/null +++ b/model-00047-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcc5d06065d2a564894657945ccfe9411762421c2c60acf91de31050cd4d84d +size 2539429936 diff --git a/model-00048-of-00048.safetensors b/model-00048-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66dc5fc40d32acc196b9686568f96f35dc95a747 --- /dev/null +++ b/model-00048-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35fff90a30ca808d86dc24f9e3eda119832ab69fb1f88ae4cccfbf0e5ee409a1 +size 1287438264 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..215064e6cfa2a56b41b5ef618d82b802a103cdfc --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,9710 @@ +{ + "metadata": { + "total_size": 31221488576 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00048.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.47.embed_tokens.weight": "model-00001-of-00048.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_b_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_a_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_a_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_b_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_b_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_a_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_a_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_b_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_b_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_a_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_a_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_b_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_b_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_a_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_a_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_b_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_b_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_a_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_a_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_b_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_a_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_b_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_a_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_a_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_b_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_b_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_a_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_a_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_b_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_a_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_b_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_a_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_a_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_b_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_a_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_b_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_a_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_a_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_b_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_b_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_a_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_a_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_b_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_b_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_a_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_a_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_b_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_b_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_a_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_a_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_b_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_b_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_a_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_a_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_b_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_b_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_a_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_a_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_b_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_b_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_a_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_a_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_b_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_b_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_a_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_a_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_b_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_b_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_a_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_a_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_b_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_b_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_a_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_a_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_b_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_b_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_a_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_a_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_b_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_b_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_a_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_a_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_b_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_b_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_a_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_a_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_b_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_b_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_a_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_a_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_b_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_b_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_a_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_a_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_b_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_b_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_a_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_a_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_b_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_b_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_a_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_a_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_b_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_b_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_a_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_a_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_b_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_b_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_a_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_a_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_b_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_a_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_b_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_a_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_a_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_b_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_a_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_b_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_a_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_a_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_b_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_a_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_b_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_a_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_a_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_b_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_b_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_a_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_a_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_b_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.32.input_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_a_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_b_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_a_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_a_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_b_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.33.input_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_a_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_b_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_a_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_a_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_b_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.34.input_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_a_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_b_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_a_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_a_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_b_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.35.input_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_b_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_a_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_a_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_b_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.36.input_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_a_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_b_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_a_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_a_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_b_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.37.input_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_a_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_a_proj_with_mqa.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_b_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_a_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_a_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_b_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.38.input_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_a_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_a_proj_with_mqa.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_b_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_a_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_a_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_b_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.39.input_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_a_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_b_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_a_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_a_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_b_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.40.input_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_a_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_a_proj_with_mqa.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_b_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_a_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_a_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_b_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.41.input_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_a_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_a_proj_with_mqa.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_b_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_a_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_a_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_b_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.42.input_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_a_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_a_proj_with_mqa.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_b_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_a_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_a_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_b_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.43.input_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_a_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_b_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_a_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_a_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_b_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.44.input_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_a_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_a_proj_with_mqa.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_b_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_a_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_a_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_b_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.45.input_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_a_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_b_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_a_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_a_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_b_proj.weight": "model-00046-of-00048.safetensors", + "lm_head.weight": "model-00047-of-00048.safetensors", + "model.layers.46.input_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.gate.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_a_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_a_proj_with_mqa.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_b_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_a_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_a_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_b_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.47.shared_head.head.weight": "model-00047-of-00048.safetensors", + "model.norm.weight": "model-00047-of-00048.safetensors", + "model.layers.47.eh_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.enorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.hnorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.input_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.gate.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_a_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_a_proj_with_mqa.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_b_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_a_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_a_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_b_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.shared_head.norm.weight": "model-00048-of-00048.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..e55d4ebc804e6777c73f1ced0c44c4b2964cea0d --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,36 @@ +{ + "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|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..aba40197a4cdb5607f4ab7a05fb0a4ee8054fd6d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d +size 20217442 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f9e45b9c5a1d2e11b7657c81be99414c6002d732 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,324 @@ +{ + "added_tokens_decoder": { + "154820": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154821": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154822": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154823": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154824": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154825": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154826": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154827": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154828": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154829": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154830": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154831": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154832": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154833": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154834": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154835": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154836": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154837": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154838": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154839": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154840": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154841": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154842": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154843": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154844": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154845": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154846": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154847": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154848": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154849": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154850": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154851": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154852": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154853": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154854": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154855": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "[MASK]", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": null, + "chat_template": "[gMASK]\n{%- if tools -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n\n{% for tool in tools %}\n{{ tool | tojson(ensure_ascii=False) }}\n{% endfor %}\n\n\nFor each function call, output the function name and arguments within the following XML format:\n{function-name}{arg-key-1}{arg-value-1}{arg-key-2}{arg-value-2}...{%- endif -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {% set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{% for m in messages %}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set reasoning_content = '' %}\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n{%- endif %}\n{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}\n{{ '' + reasoning_content.strip() + ''}}\n{%- else -%}\n{{ '' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '' + tc.name -}}\n{% 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 %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if m.content is string -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' }}\n{%- endif %}\n{{- '' }}\n{{- m.content }}\n{{- '' }}\n{%- else -%}\n<|observation|>{% for tr in m.content %}\n{{ tr.output if tr.output is defined else tr }}{% endfor -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '' if (enable_thinking is defined and not enable_thinking) else '' -}}\n{%- endif -%}" +} \ No newline at end of file