diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..aa7aacd0134a92c3c1943fdecc75cd8b7420cce6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +model.safetensors.index.json 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..d56ca11060668ec866d9654b6177c85d1ec28946 --- /dev/null +++ b/README.md @@ -0,0 +1,115 @@ +--- +language: +- en +- zh +library_name: transformers +license: mit +pipeline_tag: text-generation +base_model: +- zai-org/GLM-5.1 +tags: +- unsloth +- glm_moe_dsa +--- +
+

+

See how to run GLM-5.1 locally - Read our Guide!

+

+

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

+
+ + + + + + + + + +
+
+ +You can follow instructions in our [guide here](https://unsloth.ai/docs/models/glm-5.1). + +--- + + +# GLM-5.1 + +
+ +
+

+ đź‘‹ Join our WeChat or Discord community. +
+ đź“– Check out the GLM-5.1 blog and GLM-5 Technical report. +
+ đź“Ť Use GLM-5.1 API services on Z.ai API Platform. +
+ 🔜 GLM-5.1 will be available on chat.z.ai in the coming days. +

+ +

+ [Paper] + [GitHub] +

+ +## Introduction + +GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks). + +![bench_51](https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/bench_51.png) + +But the most meaningful leap goes beyond first-pass performance. Previous models—including GLM-5—tend to exhaust their repertoire early: they apply familiar techniques for quick initial gains, then plateau. Giving them more time doesn't help. + +GLM-5.1, by contrast, is built to stay effective on agentic tasks over much longer horizons. We've found that the model handles ambiguous problems with better judgment and stays productive over longer sessions. It breaks complex problems down, runs experiments, reads results, and identifies blockers with real precision. By revisiting its reasoning and revising its strategy through repeated iteration, GLM-5.1 sustains optimization over hundreds of rounds and thousands of tool calls. The longer it runs, the better the result. + +## Benchmark + +| | GLM-5.1 | GLM-5 | Qwen3.6-Plus | Minimax M2.7 | DeepSeek-V3.2 | Kimi K2.5 | Claude Opus 4.6 | Gemini 3.1 Pro | GPT-5.4 | +| ------------------------------------------ | ------------------ | ------------------- | ------------ | -------------------- | -------------------- | ---------- | --------------- | -------------- | ---------------- | +| HLE | 31.0 | 30.5 | 28.8 | 28.0 | 25.1 | 31.5 | 36.7 | **45.0** | 39.8 | +| HLE (w/ Tools) | 52.3 | 50.4 | 50.6 | - | 40.8 | 51.8 | **53.1*** | 51.4* | 52.1* | +| AIME 2026 | 95.3 | 95.4 | 95.1 | 89.8 | 95.1 | 94.5 | 95.6 | 98.2 | **98.7** | +| HMMT Nov. 2025 | 94.0 | **96.9** | 94.6 | 81.0 | 90.2 | 91.1 | 96.3 | 94.8 | 95.8 | +| HMMT Feb. 2026 | 82.6 | 82.8 | 87.8 | 72.7 | 79.9 | 81.3 | 84.3 | 87.3 | **91.8** | +| IMOAnswerBench | 83.8 | 82.5 | 83.8 | 66.3 | 78.3 | 81.8 | 75.3 | 81.0 | **91.4** | +| GPQA-Diamond | 86.2 | 86.0 | 90.4 | 87.0 | 82.4 | 87.6 | 91.3 | **94.3** | 92.0 | +| SWE-Bench Pro | **58.4** | 55.1 | 56.6 | 56.2 | - | 53.8 | 57.3 | 54.2 | 57.7 | +| NL2Repo | 42.7 | 35.9 | 37.9 | 39.8 | - | 32.0 | **49.8** | 33.4 | 41.3 | +| Terminal-Bench 2.0 (Terminus-2) | 63.5 | 56.2 | 61.6 | - | 39.3 | 50.8 | 65.4 | **68.5** | - | +| Terminal-Bench 2.0 (Best self-reported) | 66.5 (Claude Code) | 56.2 (Claude Code) | - | 57.0 (Claude Code) | 46.4 (Claude Code) | - | - | - | **75.1** (Codex) | +| CyberGym | **68.7** | 48.3 | - | - | 17.3 | 41.3 | 66.6 | - | - | +| BrowseComp | **68.0** | 62.0 | - | - | 51.4 | 60.6 | - | - | - | +| BrowseComp (w/ Context Manage) | 79.3 | 75.9 | - | - | 67.6 | 74.9 | 84.0 | **85.9** | 82.7 | +| τ³-Bench | 70.6 | 69.2 | 70.7 | 67.6 | 69.2 | 66.0 | 72.4 | 67.1 | **72.9** | +| MCP-Atlas (Public Set) | 71.8 | 69.2 | **74.1** | 48.8 | 62.2 | 63.8 | 73.8 | 69.2 | 67.2 | +| Tool-Decathlon | 40.7 | 38.0 | 39.8 | 46.3 | 35.2 | 27.8 | 47.2 | 48.8 | **54.6** | +| Vending Bench 2 | $5,634.00 | $4,432.12 | $5,114.87 | - | $1,034.00 | $1,198.46 | **$8,017.59** | $911.21 | $6,144.18 | +## Serve GLM-5.1 Locally + +The following open-source frameworks support local deployment of GLM-5.1: + +- [SGLang](https://github.com/sgl-project/sglang) (v0.5.10+) — see [cookbook](https://cookbook.sglang.io/autoregressive/GLM/GLM-5.1) +- [vLLM](https://github.com/vllm-project/vllm) (v0.19.0+) — see [recipes](https://github.com/vllm-project/recipes/blob/main/GLM/GLM5.md) +- [xLLM](https://github.com/jd-opensource/xllm) (v0.8.0+) — see [example](https://github.com/zai-org/GLM-5/blob/main/example/ascend.md) +- [Transformers](https://github.com/huggingface/transformers) (v0.5.3+) — see [transformers docs](https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/glm_moe_dsa.md) +- [KTransformers](https://github.com/kvcache-ai/ktransformers) (v0.5.3+) — see [tutorial](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/GLM-5.1-Tutorial.md) + +## Citation + +If you find GLM-5.1 or GLM-5 useful in your research, please cite our technical report: + +```bibtex +@misc{glm5team2026glm5vibecodingagentic, + title={GLM-5: from Vibe Coding to Agentic Engineering}, + author={GLM-5-Team and : and Aohan Zeng and Xin Lv and Zhenyu Hou and Zhengxiao Du and Qinkai Zheng and Bin Chen and Da Yin and Chendi Ge and Chenghua Huang and Chengxing Xie and Chenzheng Zhu and Congfeng Yin and Cunxiang Wang and Gengzheng Pan and Hao Zeng and Haoke Zhang and Haoran Wang and Huilong Chen and Jiajie Zhang and Jian Jiao and Jiaqi Guo and Jingsen Wang and Jingzhao Du and Jinzhu Wu and Kedong Wang and Lei Li and Lin Fan and Lucen Zhong and Mingdao Liu and Mingming Zhao and Pengfan Du and Qian Dong and Rui Lu and Shuang-Li and Shulin Cao and Song Liu and Ting Jiang and Xiaodong Chen and Xiaohan Zhang and Xuancheng Huang and Xuezhen Dong and Yabo Xu and Yao Wei and Yifan An and Yilin Niu and Yitong Zhu and Yuanhao Wen and Yukuo Cen and Yushi Bai and Zhongpei Qiao and Zihan Wang and Zikang Wang and Zilin Zhu and Ziqiang Liu and Zixuan Li and Bojie Wang and Bosi Wen and Can Huang and Changpeng Cai and Chao Yu and Chen Li and Chengwei Hu and Chenhui Zhang and Dan Zhang and Daoyan Lin and Dayong Yang and Di Wang and Ding Ai and Erle Zhu and Fangzhou Yi and Feiyu Chen and Guohong Wen and Hailong Sun and Haisha Zhao and Haiyi Hu and Hanchen Zhang and Hanrui Liu and Hanyu Zhang and Hao Peng and Hao Tai and Haobo Zhang and He Liu and Hongwei Wang and Hongxi Yan and Hongyu Ge and Huan Liu and Huanpeng Chu and Jia'ni Zhao and Jiachen Wang and Jiajing Zhao and Jiamin Ren and Jiapeng Wang and Jiaxin Zhang and Jiayi Gui and Jiayue Zhao and Jijie Li and Jing An and Jing Li and Jingwei Yuan and Jinhua Du and Jinxin Liu and Junkai Zhi and Junwen Duan and Kaiyue Zhou and Kangjian Wei and Ke Wang and Keyun Luo and Laiqiang Zhang and Leigang Sha and Liang Xu and Lindong Wu and Lintao Ding and Lu Chen and Minghao Li and Nianyi Lin and Pan Ta and Qiang Zou and Rongjun Song and Ruiqi Yang and Shangqing Tu and Shangtong Yang and Shaoxiang Wu and Shengyan Zhang and Shijie Li and Shuang Li and Shuyi Fan and Wei Qin and Wei Tian and Weining Zhang and Wenbo Yu and Wenjie Liang and Xiang Kuang and Xiangmeng Cheng and Xiangyang Li and Xiaoquan Yan and Xiaowei Hu and Xiaoying Ling and Xing Fan and Xingye Xia and Xinyuan Zhang and Xinze Zhang and Xirui Pan and Xu Zou and Xunkai Zhang and Yadi Liu and Yandong Wu and Yanfu Li and Yidong Wang and Yifan Zhu and Yijun Tan and Yilin Zhou and Yiming Pan and Ying Zhang and Yinpei Su and Yipeng Geng and Yong Yan and Yonglin Tan and Yuean Bi and Yuhan Shen and Yuhao Yang and Yujiang Li and Yunan Liu and Yunqing Wang and Yuntao Li and Yurong Wu and Yutao Zhang and Yuxi Duan and Yuxuan Zhang and Zezhen Liu and Zhengtao Jiang and Zhenhe Yan and Zheyu Zhang and Zhixiang Wei and Zhuo Chen and Zhuoer Feng and Zijun Yao and Ziwei Chai and Ziyuan Wang and Zuzhou Zhang and Bin Xu and Minlie Huang and Hongning Wang and Juanzi Li and Yuxiao Dong and Jie Tang}, + year={2026}, + eprint={2602.15763}, + archivePrefix={arXiv}, + primaryClass={cs.LG}, + url={https://arxiv.org/abs/2602.15763}, +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..0093efaa15b9ee3b0d8799ec64933fe0897b6687 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,117 @@ +[gMASK] +{%- if tools -%} +{%- macro tool_to_json(tool) -%} + {%- set ns_tool = namespace(first=true) -%} + {{ '{' -}} + {%- for k, v in tool.items() -%} + {%- if k != 'defer_loading' and k != 'strict' -%} + {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%} + {%- set ns_tool.first = false -%} + "{{ k }}": {{ v | tojson(ensure_ascii=False) }} + {%- endif -%} + {%- endfor -%} + {{- '}' -}} +{%- endmacro -%} +<|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 %} +{%- if 'function' in tool -%} + {%- set tool = tool['function'] -%} +{%- endif -%} +{% if tool.defer_loading is not defined or not tool.defer_loading %} +{{ tool_to_json(tool) }} +{% endif %} +{% 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, thinking_indices='') -%} +{%- for m in messages %} + {%- if m.role == 'user' %} + {%- set ns.last_user_index = loop.index0 -%} + {%- elif m.role == 'assistant' %} + {%- if m.reasoning_content is string %} + {%- set ns.thinking_indices = ns.thinking_indices ~ ',' ~ ns.last_user_index ~ ',' -%} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- set ns.has_thinking = false -%} +{%- for m in messages -%} +{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}{% set ns.has_thinking = (',' ~ loop.index0 ~ ',') in ns.thinking_indices -%} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- elif '' in content %} + {%- set reasoning_content = content.split('')[0].split('')[-1] %} + {%- set content = content.split('')[-1] %} +{%- elif loop.index0 > ns.last_user_index and not (enable_thinking is defined and not enable_thinking) %} + {%- set reasoning_content = '' %} +{%- elif loop.index0 < ns.last_user_index and ns.has_thinking %} + {%- set reasoning_content = '' %} +{%- endif %} +{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%} +{{ '' + reasoning_content + ''}} +{%- 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 loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' -}} +{%- endif %} +{%- if m.content is string -%} + {{- '' + m.content + '' -}} +{%- else -%} + {{- '\n' -}} + {% for tr in m.content %} + {%- for tool in tools -%} + {%- if 'function' in tool -%} + {%- set tool = tool['function'] -%} + {%- endif -%} + {%- if tool.name == tr.name -%} + {{- tool_to_json(tool) + '\n' -}} + {%- endif -%} + {%- endfor -%} + {%- 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..e5ac5ceb7bc918aff3fc517f44fea80e9b5914dc --- /dev/null +++ b/config.json @@ -0,0 +1,862 @@ +{ + "architectures": [ + "GlmMoeDsaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "torch_dtype": "bfloat16", + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "ep_size": 1, + "first_k_dense_replace": 3, + "hidden_act": "silu", + "hidden_size": 6144, + "index_head_dim": 128, + "index_n_heads": 32, + "index_topk": 2048, + "indexer_rope_interleave": true, + "initializer_range": 0.02, + "intermediate_size": 12288, + "kv_lora_rank": 512, + "max_position_embeddings": 202752, + "mlp_layer_types": [ + "dense", + "dense", + "dense", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse" + ], + "model_type": "glm_moe_dsa", + "moe_intermediate_size": 2048, + "moe_layer_freq": 1, + "n_group": 1, + "n_routed_experts": 256, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 64, + "num_experts_per_tok": 8, + "num_hidden_layers": 78, + "num_key_value_heads": 64, + "num_nextn_predict_layers": 1, + "pad_token_id": 154821, + "pretraining_tp": 1, + "q_lora_rank": 2048, + "qk_head_dim": 256, + "qk_nope_head_dim": 192, + "qk_rope_head_dim": 64, + "quantization_config": { + "activation_scheme": "dynamic", + "fmt": "e4m3", + "modules_to_not_convert": [ + "lm_head", + "model.embed_tokens", + "model.layers.0.input_layernorm", + "model.layers.0.post_attention_layernorm", + "model.layers.0.self_attn.indexer.k_norm", + "model.layers.0.self_attn.indexer.k_norm.bias", + "model.layers.0.self_attn.indexers_proj", + "model.layers.0.self_attn.kv_a_layernorm", + "model.layers.0.self_attn.q_a_layernorm", + "model.layers.1.input_layernorm", + "model.layers.1.post_attention_layernorm", + "model.layers.1.self_attn.indexer.k_norm", + "model.layers.1.self_attn.indexer.k_norm.bias", + "model.layers.1.self_attn.indexers_proj", + "model.layers.1.self_attn.kv_a_layernorm", + "model.layers.1.self_attn.q_a_layernorm", + "model.layers.2.input_layernorm", + "model.layers.2.post_attention_layernorm", + "model.layers.2.self_attn.indexer.k_norm", + "model.layers.2.self_attn.indexer.k_norm.bias", + "model.layers.2.self_attn.indexers_proj", + "model.layers.2.self_attn.kv_a_layernorm", + "model.layers.2.self_attn.q_a_layernorm", + "model.layers.3.input_layernorm", + "model.layers.3.mlp.gate", + "model.layers.3.mlp.gate.e_score_correction_bias", + "model.layers.3.post_attention_layernorm", + "model.layers.3.self_attn.indexer.k_norm", + "model.layers.3.self_attn.indexer.k_norm.bias", + "model.layers.3.self_attn.indexers_proj", + "model.layers.3.self_attn.kv_a_layernorm", + "model.layers.3.self_attn.q_a_layernorm", + "model.layers.4.input_layernorm", + "model.layers.4.mlp.gate", + "model.layers.4.mlp.gate.e_score_correction_bias", + "model.layers.4.post_attention_layernorm", + "model.layers.4.self_attn.indexer.k_norm", + "model.layers.4.self_attn.indexer.k_norm.bias", + "model.layers.4.self_attn.indexers_proj", + "model.layers.4.self_attn.kv_a_layernorm", + "model.layers.4.self_attn.q_a_layernorm", + "model.layers.5.input_layernorm", + "model.layers.5.mlp.gate", + "model.layers.5.mlp.gate.e_score_correction_bias", + "model.layers.5.post_attention_layernorm", + "model.layers.5.self_attn.indexer.k_norm", + "model.layers.5.self_attn.indexer.k_norm.bias", + "model.layers.5.self_attn.indexers_proj", + "model.layers.5.self_attn.kv_a_layernorm", + "model.layers.5.self_attn.q_a_layernorm", + "model.layers.6.input_layernorm", + "model.layers.6.mlp.gate", + "model.layers.6.mlp.gate.e_score_correction_bias", + "model.layers.6.post_attention_layernorm", + "model.layers.6.self_attn.indexer.k_norm", + "model.layers.6.self_attn.indexer.k_norm.bias", + "model.layers.6.self_attn.indexers_proj", + "model.layers.6.self_attn.kv_a_layernorm", + "model.layers.6.self_attn.q_a_layernorm", + "model.layers.7.input_layernorm", + "model.layers.7.mlp.gate", + "model.layers.7.mlp.gate.e_score_correction_bias", + "model.layers.7.post_attention_layernorm", + "model.layers.7.self_attn.indexer.k_norm", + "model.layers.7.self_attn.indexer.k_norm.bias", + "model.layers.7.self_attn.indexers_proj", + "model.layers.7.self_attn.kv_a_layernorm", + "model.layers.7.self_attn.q_a_layernorm", + "model.layers.8.input_layernorm", + "model.layers.8.mlp.gate", + "model.layers.8.mlp.gate.e_score_correction_bias", + "model.layers.8.post_attention_layernorm", + "model.layers.8.self_attn.indexer.k_norm", + "model.layers.8.self_attn.indexer.k_norm.bias", + "model.layers.8.self_attn.indexers_proj", + "model.layers.8.self_attn.kv_a_layernorm", + "model.layers.8.self_attn.q_a_layernorm", + "model.layers.9.input_layernorm", + "model.layers.9.mlp.gate", + "model.layers.9.mlp.gate.e_score_correction_bias", + "model.layers.9.post_attention_layernorm", + "model.layers.9.self_attn.indexer.k_norm", + "model.layers.9.self_attn.indexer.k_norm.bias", + "model.layers.9.self_attn.indexers_proj", + "model.layers.9.self_attn.kv_a_layernorm", + "model.layers.9.self_attn.q_a_layernorm", + "model.layers.10.input_layernorm", + "model.layers.10.mlp.gate", + "model.layers.10.mlp.gate.e_score_correction_bias", + "model.layers.10.post_attention_layernorm", + "model.layers.10.self_attn.indexer.k_norm", + "model.layers.10.self_attn.indexer.k_norm.bias", + "model.layers.10.self_attn.indexers_proj", + "model.layers.10.self_attn.kv_a_layernorm", + "model.layers.10.self_attn.q_a_layernorm", + "model.layers.11.input_layernorm", + "model.layers.11.mlp.gate", + "model.layers.11.mlp.gate.e_score_correction_bias", + "model.layers.11.post_attention_layernorm", + "model.layers.11.self_attn.indexer.k_norm", + "model.layers.11.self_attn.indexer.k_norm.bias", + "model.layers.11.self_attn.indexers_proj", + "model.layers.11.self_attn.kv_a_layernorm", + "model.layers.11.self_attn.q_a_layernorm", + "model.layers.12.input_layernorm", + "model.layers.12.mlp.gate", + "model.layers.12.mlp.gate.e_score_correction_bias", + "model.layers.12.post_attention_layernorm", + "model.layers.12.self_attn.indexer.k_norm", + "model.layers.12.self_attn.indexer.k_norm.bias", + "model.layers.12.self_attn.indexers_proj", + "model.layers.12.self_attn.kv_a_layernorm", + "model.layers.12.self_attn.q_a_layernorm", + "model.layers.13.input_layernorm", + "model.layers.13.mlp.gate", + "model.layers.13.mlp.gate.e_score_correction_bias", + "model.layers.13.post_attention_layernorm", + "model.layers.13.self_attn.indexer.k_norm", + "model.layers.13.self_attn.indexer.k_norm.bias", + "model.layers.13.self_attn.indexers_proj", + "model.layers.13.self_attn.kv_a_layernorm", + "model.layers.13.self_attn.q_a_layernorm", + "model.layers.14.input_layernorm", + "model.layers.14.mlp.gate", + "model.layers.14.mlp.gate.e_score_correction_bias", + "model.layers.14.post_attention_layernorm", + "model.layers.14.self_attn.indexer.k_norm", + "model.layers.14.self_attn.indexer.k_norm.bias", + "model.layers.14.self_attn.indexers_proj", + "model.layers.14.self_attn.kv_a_layernorm", + "model.layers.14.self_attn.q_a_layernorm", + "model.layers.15.input_layernorm", + "model.layers.15.mlp.gate", + "model.layers.15.mlp.gate.e_score_correction_bias", + "model.layers.15.post_attention_layernorm", + "model.layers.15.self_attn.indexer.k_norm", + "model.layers.15.self_attn.indexer.k_norm.bias", + "model.layers.15.self_attn.indexers_proj", + "model.layers.15.self_attn.kv_a_layernorm", + "model.layers.15.self_attn.q_a_layernorm", + "model.layers.16.input_layernorm", + "model.layers.16.mlp.gate", + "model.layers.16.mlp.gate.e_score_correction_bias", + "model.layers.16.post_attention_layernorm", + "model.layers.16.self_attn.indexer.k_norm", + "model.layers.16.self_attn.indexer.k_norm.bias", + "model.layers.16.self_attn.indexers_proj", + "model.layers.16.self_attn.kv_a_layernorm", + "model.layers.16.self_attn.q_a_layernorm", + "model.layers.17.input_layernorm", + "model.layers.17.mlp.gate", + "model.layers.17.mlp.gate.e_score_correction_bias", + "model.layers.17.post_attention_layernorm", + "model.layers.17.self_attn.indexer.k_norm", + "model.layers.17.self_attn.indexer.k_norm.bias", + "model.layers.17.self_attn.indexers_proj", + "model.layers.17.self_attn.kv_a_layernorm", + "model.layers.17.self_attn.q_a_layernorm", + "model.layers.18.input_layernorm", + "model.layers.18.mlp.gate", + "model.layers.18.mlp.gate.e_score_correction_bias", + "model.layers.18.post_attention_layernorm", + "model.layers.18.self_attn.indexer.k_norm", + "model.layers.18.self_attn.indexer.k_norm.bias", + "model.layers.18.self_attn.indexers_proj", + "model.layers.18.self_attn.kv_a_layernorm", + "model.layers.18.self_attn.q_a_layernorm", + "model.layers.19.input_layernorm", + "model.layers.19.mlp.gate", + "model.layers.19.mlp.gate.e_score_correction_bias", + "model.layers.19.post_attention_layernorm", + "model.layers.19.self_attn.indexer.k_norm", + "model.layers.19.self_attn.indexer.k_norm.bias", + "model.layers.19.self_attn.indexers_proj", + "model.layers.19.self_attn.kv_a_layernorm", + "model.layers.19.self_attn.q_a_layernorm", + "model.layers.20.input_layernorm", + "model.layers.20.mlp.gate", + "model.layers.20.mlp.gate.e_score_correction_bias", + "model.layers.20.post_attention_layernorm", + "model.layers.20.self_attn.indexer.k_norm", + "model.layers.20.self_attn.indexer.k_norm.bias", + "model.layers.20.self_attn.indexers_proj", + "model.layers.20.self_attn.kv_a_layernorm", + "model.layers.20.self_attn.q_a_layernorm", + "model.layers.21.input_layernorm", + "model.layers.21.mlp.gate", + "model.layers.21.mlp.gate.e_score_correction_bias", + "model.layers.21.post_attention_layernorm", + "model.layers.21.self_attn.indexer.k_norm", + "model.layers.21.self_attn.indexer.k_norm.bias", + "model.layers.21.self_attn.indexers_proj", + "model.layers.21.self_attn.kv_a_layernorm", + "model.layers.21.self_attn.q_a_layernorm", + "model.layers.22.input_layernorm", + "model.layers.22.mlp.gate", + "model.layers.22.mlp.gate.e_score_correction_bias", + "model.layers.22.post_attention_layernorm", + "model.layers.22.self_attn.indexer.k_norm", + "model.layers.22.self_attn.indexer.k_norm.bias", + "model.layers.22.self_attn.indexers_proj", + "model.layers.22.self_attn.kv_a_layernorm", + "model.layers.22.self_attn.q_a_layernorm", + "model.layers.23.input_layernorm", + "model.layers.23.mlp.gate", + "model.layers.23.mlp.gate.e_score_correction_bias", + "model.layers.23.post_attention_layernorm", + "model.layers.23.self_attn.indexer.k_norm", + "model.layers.23.self_attn.indexer.k_norm.bias", + "model.layers.23.self_attn.indexers_proj", + "model.layers.23.self_attn.kv_a_layernorm", + "model.layers.23.self_attn.q_a_layernorm", + "model.layers.24.input_layernorm", + "model.layers.24.mlp.gate", + "model.layers.24.mlp.gate.e_score_correction_bias", + "model.layers.24.post_attention_layernorm", + "model.layers.24.self_attn.indexer.k_norm", + "model.layers.24.self_attn.indexer.k_norm.bias", + "model.layers.24.self_attn.indexers_proj", + "model.layers.24.self_attn.kv_a_layernorm", + "model.layers.24.self_attn.q_a_layernorm", + "model.layers.25.input_layernorm", + "model.layers.25.mlp.gate", + "model.layers.25.mlp.gate.e_score_correction_bias", + "model.layers.25.post_attention_layernorm", + "model.layers.25.self_attn.indexer.k_norm", + "model.layers.25.self_attn.indexer.k_norm.bias", + "model.layers.25.self_attn.indexers_proj", + "model.layers.25.self_attn.kv_a_layernorm", + "model.layers.25.self_attn.q_a_layernorm", + "model.layers.26.input_layernorm", + "model.layers.26.mlp.gate", + "model.layers.26.mlp.gate.e_score_correction_bias", + "model.layers.26.post_attention_layernorm", + "model.layers.26.self_attn.indexer.k_norm", + "model.layers.26.self_attn.indexer.k_norm.bias", + "model.layers.26.self_attn.indexers_proj", + "model.layers.26.self_attn.kv_a_layernorm", + "model.layers.26.self_attn.q_a_layernorm", + "model.layers.27.input_layernorm", + "model.layers.27.mlp.gate", + "model.layers.27.mlp.gate.e_score_correction_bias", + "model.layers.27.post_attention_layernorm", + "model.layers.27.self_attn.indexer.k_norm", + "model.layers.27.self_attn.indexer.k_norm.bias", + "model.layers.27.self_attn.indexers_proj", + "model.layers.27.self_attn.kv_a_layernorm", + "model.layers.27.self_attn.q_a_layernorm", + "model.layers.28.input_layernorm", + "model.layers.28.mlp.gate", + "model.layers.28.mlp.gate.e_score_correction_bias", + "model.layers.28.post_attention_layernorm", + "model.layers.28.self_attn.indexer.k_norm", + "model.layers.28.self_attn.indexer.k_norm.bias", + "model.layers.28.self_attn.indexers_proj", + "model.layers.28.self_attn.kv_a_layernorm", + "model.layers.28.self_attn.q_a_layernorm", + "model.layers.29.input_layernorm", + "model.layers.29.mlp.gate", + "model.layers.29.mlp.gate.e_score_correction_bias", + "model.layers.29.post_attention_layernorm", + "model.layers.29.self_attn.indexer.k_norm", + "model.layers.29.self_attn.indexer.k_norm.bias", + "model.layers.29.self_attn.indexers_proj", + "model.layers.29.self_attn.kv_a_layernorm", + "model.layers.29.self_attn.q_a_layernorm", + "model.layers.30.input_layernorm", + "model.layers.30.mlp.gate", + "model.layers.30.mlp.gate.e_score_correction_bias", + "model.layers.30.post_attention_layernorm", + "model.layers.30.self_attn.indexer.k_norm", + "model.layers.30.self_attn.indexer.k_norm.bias", + "model.layers.30.self_attn.indexers_proj", + "model.layers.30.self_attn.kv_a_layernorm", + "model.layers.30.self_attn.q_a_layernorm", + "model.layers.31.input_layernorm", + "model.layers.31.mlp.gate", + "model.layers.31.mlp.gate.e_score_correction_bias", + "model.layers.31.post_attention_layernorm", + "model.layers.31.self_attn.indexer.k_norm", + "model.layers.31.self_attn.indexer.k_norm.bias", + "model.layers.31.self_attn.indexers_proj", + "model.layers.31.self_attn.kv_a_layernorm", + "model.layers.31.self_attn.q_a_layernorm", + "model.layers.32.input_layernorm", + "model.layers.32.mlp.gate", + "model.layers.32.mlp.gate.e_score_correction_bias", + "model.layers.32.post_attention_layernorm", + "model.layers.32.self_attn.indexer.k_norm", + "model.layers.32.self_attn.indexer.k_norm.bias", + "model.layers.32.self_attn.indexers_proj", + "model.layers.32.self_attn.kv_a_layernorm", + "model.layers.32.self_attn.q_a_layernorm", + "model.layers.33.input_layernorm", + "model.layers.33.mlp.gate", + "model.layers.33.mlp.gate.e_score_correction_bias", + "model.layers.33.post_attention_layernorm", + "model.layers.33.self_attn.indexer.k_norm", + "model.layers.33.self_attn.indexer.k_norm.bias", + "model.layers.33.self_attn.indexers_proj", + "model.layers.33.self_attn.kv_a_layernorm", + "model.layers.33.self_attn.q_a_layernorm", + "model.layers.34.input_layernorm", + "model.layers.34.mlp.gate", + "model.layers.34.mlp.gate.e_score_correction_bias", + "model.layers.34.post_attention_layernorm", + "model.layers.34.self_attn.indexer.k_norm", + "model.layers.34.self_attn.indexer.k_norm.bias", + "model.layers.34.self_attn.indexers_proj", + "model.layers.34.self_attn.kv_a_layernorm", + "model.layers.34.self_attn.q_a_layernorm", + "model.layers.35.input_layernorm", + "model.layers.35.mlp.gate", + "model.layers.35.mlp.gate.e_score_correction_bias", + "model.layers.35.post_attention_layernorm", + "model.layers.35.self_attn.indexer.k_norm", + "model.layers.35.self_attn.indexer.k_norm.bias", + "model.layers.35.self_attn.indexers_proj", + "model.layers.35.self_attn.kv_a_layernorm", + "model.layers.35.self_attn.q_a_layernorm", + "model.layers.36.input_layernorm", + "model.layers.36.mlp.gate", + "model.layers.36.mlp.gate.e_score_correction_bias", + "model.layers.36.post_attention_layernorm", + "model.layers.36.self_attn.indexer.k_norm", + "model.layers.36.self_attn.indexer.k_norm.bias", + "model.layers.36.self_attn.indexers_proj", + "model.layers.36.self_attn.kv_a_layernorm", + "model.layers.36.self_attn.q_a_layernorm", + "model.layers.37.input_layernorm", + "model.layers.37.mlp.gate", + "model.layers.37.mlp.gate.e_score_correction_bias", + "model.layers.37.post_attention_layernorm", + "model.layers.37.self_attn.indexer.k_norm", + "model.layers.37.self_attn.indexer.k_norm.bias", + "model.layers.37.self_attn.indexers_proj", + "model.layers.37.self_attn.kv_a_layernorm", + "model.layers.37.self_attn.q_a_layernorm", + "model.layers.38.input_layernorm", + "model.layers.38.mlp.gate", + "model.layers.38.mlp.gate.e_score_correction_bias", + "model.layers.38.post_attention_layernorm", + "model.layers.38.self_attn.indexer.k_norm", + "model.layers.38.self_attn.indexer.k_norm.bias", + "model.layers.38.self_attn.indexers_proj", + "model.layers.38.self_attn.kv_a_layernorm", + "model.layers.38.self_attn.q_a_layernorm", + "model.layers.39.input_layernorm", + "model.layers.39.mlp.gate", + "model.layers.39.mlp.gate.e_score_correction_bias", + "model.layers.39.post_attention_layernorm", + "model.layers.39.self_attn.indexer.k_norm", + "model.layers.39.self_attn.indexer.k_norm.bias", + "model.layers.39.self_attn.indexers_proj", + "model.layers.39.self_attn.kv_a_layernorm", + "model.layers.39.self_attn.q_a_layernorm", + "model.layers.40.input_layernorm", + "model.layers.40.mlp.gate", + "model.layers.40.mlp.gate.e_score_correction_bias", + "model.layers.40.post_attention_layernorm", + "model.layers.40.self_attn.indexer.k_norm", + "model.layers.40.self_attn.indexer.k_norm.bias", + "model.layers.40.self_attn.indexers_proj", + "model.layers.40.self_attn.kv_a_layernorm", + "model.layers.40.self_attn.q_a_layernorm", + "model.layers.41.input_layernorm", + "model.layers.41.mlp.gate", + "model.layers.41.mlp.gate.e_score_correction_bias", + "model.layers.41.post_attention_layernorm", + "model.layers.41.self_attn.indexer.k_norm", + "model.layers.41.self_attn.indexer.k_norm.bias", + "model.layers.41.self_attn.indexers_proj", + "model.layers.41.self_attn.kv_a_layernorm", + "model.layers.41.self_attn.q_a_layernorm", + "model.layers.42.input_layernorm", + "model.layers.42.mlp.gate", + "model.layers.42.mlp.gate.e_score_correction_bias", + "model.layers.42.post_attention_layernorm", + "model.layers.42.self_attn.indexer.k_norm", + "model.layers.42.self_attn.indexer.k_norm.bias", + "model.layers.42.self_attn.indexers_proj", + "model.layers.42.self_attn.kv_a_layernorm", + "model.layers.42.self_attn.q_a_layernorm", + "model.layers.43.input_layernorm", + "model.layers.43.mlp.gate", + "model.layers.43.mlp.gate.e_score_correction_bias", + "model.layers.43.post_attention_layernorm", + "model.layers.43.self_attn.indexer.k_norm", + "model.layers.43.self_attn.indexer.k_norm.bias", + "model.layers.43.self_attn.indexers_proj", + "model.layers.43.self_attn.kv_a_layernorm", + "model.layers.43.self_attn.q_a_layernorm", + "model.layers.44.input_layernorm", + "model.layers.44.mlp.gate", + "model.layers.44.mlp.gate.e_score_correction_bias", + "model.layers.44.post_attention_layernorm", + "model.layers.44.self_attn.indexer.k_norm", + "model.layers.44.self_attn.indexer.k_norm.bias", + "model.layers.44.self_attn.indexers_proj", + "model.layers.44.self_attn.kv_a_layernorm", + "model.layers.44.self_attn.q_a_layernorm", + "model.layers.45.input_layernorm", + "model.layers.45.mlp.gate", + "model.layers.45.mlp.gate.e_score_correction_bias", + "model.layers.45.post_attention_layernorm", + "model.layers.45.self_attn.indexer.k_norm", + "model.layers.45.self_attn.indexer.k_norm.bias", + "model.layers.45.self_attn.indexers_proj", + "model.layers.45.self_attn.kv_a_layernorm", + "model.layers.45.self_attn.q_a_layernorm", + "model.layers.46.input_layernorm", + "model.layers.46.mlp.gate", + "model.layers.46.mlp.gate.e_score_correction_bias", + "model.layers.46.post_attention_layernorm", + "model.layers.46.self_attn.indexer.k_norm", + "model.layers.46.self_attn.indexer.k_norm.bias", + "model.layers.46.self_attn.indexers_proj", + "model.layers.46.self_attn.kv_a_layernorm", + "model.layers.46.self_attn.q_a_layernorm", + "model.layers.47.input_layernorm", + "model.layers.47.mlp.gate", + "model.layers.47.mlp.gate.e_score_correction_bias", + "model.layers.47.post_attention_layernorm", + "model.layers.47.self_attn.indexer.k_norm", + "model.layers.47.self_attn.indexer.k_norm.bias", + "model.layers.47.self_attn.indexers_proj", + "model.layers.47.self_attn.kv_a_layernorm", + "model.layers.47.self_attn.q_a_layernorm", + "model.layers.48.input_layernorm", + "model.layers.48.mlp.gate", + "model.layers.48.mlp.gate.e_score_correction_bias", + "model.layers.48.post_attention_layernorm", + "model.layers.48.self_attn.indexer.k_norm", + "model.layers.48.self_attn.indexer.k_norm.bias", + "model.layers.48.self_attn.indexers_proj", + "model.layers.48.self_attn.kv_a_layernorm", + "model.layers.48.self_attn.q_a_layernorm", + "model.layers.49.input_layernorm", + "model.layers.49.mlp.gate", + "model.layers.49.mlp.gate.e_score_correction_bias", + "model.layers.49.post_attention_layernorm", + "model.layers.49.self_attn.indexer.k_norm", + "model.layers.49.self_attn.indexer.k_norm.bias", + "model.layers.49.self_attn.indexers_proj", + "model.layers.49.self_attn.kv_a_layernorm", + "model.layers.49.self_attn.q_a_layernorm", + "model.layers.50.input_layernorm", + "model.layers.50.mlp.gate", + "model.layers.50.mlp.gate.e_score_correction_bias", + "model.layers.50.post_attention_layernorm", + "model.layers.50.self_attn.indexer.k_norm", + "model.layers.50.self_attn.indexer.k_norm.bias", + "model.layers.50.self_attn.indexers_proj", + "model.layers.50.self_attn.kv_a_layernorm", + "model.layers.50.self_attn.q_a_layernorm", + "model.layers.51.input_layernorm", + "model.layers.51.mlp.gate", + "model.layers.51.mlp.gate.e_score_correction_bias", + "model.layers.51.post_attention_layernorm", + "model.layers.51.self_attn.indexer.k_norm", + "model.layers.51.self_attn.indexer.k_norm.bias", + "model.layers.51.self_attn.indexers_proj", + "model.layers.51.self_attn.kv_a_layernorm", + "model.layers.51.self_attn.q_a_layernorm", + "model.layers.52.input_layernorm", + "model.layers.52.mlp.gate", + "model.layers.52.mlp.gate.e_score_correction_bias", + "model.layers.52.post_attention_layernorm", + "model.layers.52.self_attn.indexer.k_norm", + "model.layers.52.self_attn.indexer.k_norm.bias", + "model.layers.52.self_attn.indexers_proj", + "model.layers.52.self_attn.kv_a_layernorm", + "model.layers.52.self_attn.q_a_layernorm", + "model.layers.53.input_layernorm", + "model.layers.53.mlp.gate", + "model.layers.53.mlp.gate.e_score_correction_bias", + "model.layers.53.post_attention_layernorm", + "model.layers.53.self_attn.indexer.k_norm", + "model.layers.53.self_attn.indexer.k_norm.bias", + "model.layers.53.self_attn.indexers_proj", + "model.layers.53.self_attn.kv_a_layernorm", + "model.layers.53.self_attn.q_a_layernorm", + "model.layers.54.input_layernorm", + "model.layers.54.mlp.gate", + "model.layers.54.mlp.gate.e_score_correction_bias", + "model.layers.54.post_attention_layernorm", + "model.layers.54.self_attn.indexer.k_norm", + "model.layers.54.self_attn.indexer.k_norm.bias", + "model.layers.54.self_attn.indexers_proj", + "model.layers.54.self_attn.kv_a_layernorm", + "model.layers.54.self_attn.q_a_layernorm", + "model.layers.55.input_layernorm", + "model.layers.55.mlp.gate", + "model.layers.55.mlp.gate.e_score_correction_bias", + "model.layers.55.post_attention_layernorm", + "model.layers.55.self_attn.indexer.k_norm", + "model.layers.55.self_attn.indexer.k_norm.bias", + "model.layers.55.self_attn.indexers_proj", + "model.layers.55.self_attn.kv_a_layernorm", + "model.layers.55.self_attn.q_a_layernorm", + "model.layers.56.input_layernorm", + "model.layers.56.mlp.gate", + "model.layers.56.mlp.gate.e_score_correction_bias", + "model.layers.56.post_attention_layernorm", + "model.layers.56.self_attn.indexer.k_norm", + "model.layers.56.self_attn.indexer.k_norm.bias", + "model.layers.56.self_attn.indexers_proj", + "model.layers.56.self_attn.kv_a_layernorm", + "model.layers.56.self_attn.q_a_layernorm", + "model.layers.57.input_layernorm", + "model.layers.57.mlp.gate", + "model.layers.57.mlp.gate.e_score_correction_bias", + "model.layers.57.post_attention_layernorm", + "model.layers.57.self_attn.indexer.k_norm", + "model.layers.57.self_attn.indexer.k_norm.bias", + "model.layers.57.self_attn.indexers_proj", + "model.layers.57.self_attn.kv_a_layernorm", + "model.layers.57.self_attn.q_a_layernorm", + "model.layers.58.input_layernorm", + "model.layers.58.mlp.gate", + "model.layers.58.mlp.gate.e_score_correction_bias", + "model.layers.58.post_attention_layernorm", + "model.layers.58.self_attn.indexer.k_norm", + "model.layers.58.self_attn.indexer.k_norm.bias", + "model.layers.58.self_attn.indexers_proj", + "model.layers.58.self_attn.kv_a_layernorm", + "model.layers.58.self_attn.q_a_layernorm", + "model.layers.59.input_layernorm", + "model.layers.59.mlp.gate", + "model.layers.59.mlp.gate.e_score_correction_bias", + "model.layers.59.post_attention_layernorm", + "model.layers.59.self_attn.indexer.k_norm", + "model.layers.59.self_attn.indexer.k_norm.bias", + "model.layers.59.self_attn.indexers_proj", + "model.layers.59.self_attn.kv_a_layernorm", + "model.layers.59.self_attn.q_a_layernorm", + "model.layers.60.input_layernorm", + "model.layers.60.mlp.gate", + "model.layers.60.mlp.gate.e_score_correction_bias", + "model.layers.60.post_attention_layernorm", + "model.layers.60.self_attn.indexer.k_norm", + "model.layers.60.self_attn.indexer.k_norm.bias", + "model.layers.60.self_attn.indexers_proj", + "model.layers.60.self_attn.kv_a_layernorm", + "model.layers.60.self_attn.q_a_layernorm", + "model.layers.61.input_layernorm", + "model.layers.61.mlp.gate", + "model.layers.61.mlp.gate.e_score_correction_bias", + "model.layers.61.post_attention_layernorm", + "model.layers.61.self_attn.indexer.k_norm", + "model.layers.61.self_attn.indexer.k_norm.bias", + "model.layers.61.self_attn.indexers_proj", + "model.layers.61.self_attn.kv_a_layernorm", + "model.layers.61.self_attn.q_a_layernorm", + "model.layers.62.input_layernorm", + "model.layers.62.mlp.gate", + "model.layers.62.mlp.gate.e_score_correction_bias", + "model.layers.62.post_attention_layernorm", + "model.layers.62.self_attn.indexer.k_norm", + "model.layers.62.self_attn.indexer.k_norm.bias", + "model.layers.62.self_attn.indexers_proj", + "model.layers.62.self_attn.kv_a_layernorm", + "model.layers.62.self_attn.q_a_layernorm", + "model.layers.63.input_layernorm", + "model.layers.63.mlp.gate", + "model.layers.63.mlp.gate.e_score_correction_bias", + "model.layers.63.post_attention_layernorm", + "model.layers.63.self_attn.indexer.k_norm", + "model.layers.63.self_attn.indexer.k_norm.bias", + "model.layers.63.self_attn.indexers_proj", + "model.layers.63.self_attn.kv_a_layernorm", + "model.layers.63.self_attn.q_a_layernorm", + "model.layers.64.input_layernorm", + "model.layers.64.mlp.gate", + "model.layers.64.mlp.gate.e_score_correction_bias", + "model.layers.64.post_attention_layernorm", + "model.layers.64.self_attn.indexer.k_norm", + "model.layers.64.self_attn.indexer.k_norm.bias", + "model.layers.64.self_attn.indexers_proj", + "model.layers.64.self_attn.kv_a_layernorm", + "model.layers.64.self_attn.q_a_layernorm", + "model.layers.65.input_layernorm", + "model.layers.65.mlp.gate", + "model.layers.65.mlp.gate.e_score_correction_bias", + "model.layers.65.post_attention_layernorm", + "model.layers.65.self_attn.indexer.k_norm", + "model.layers.65.self_attn.indexer.k_norm.bias", + "model.layers.65.self_attn.indexers_proj", + "model.layers.65.self_attn.kv_a_layernorm", + "model.layers.65.self_attn.q_a_layernorm", + "model.layers.66.input_layernorm", + "model.layers.66.mlp.gate", + "model.layers.66.mlp.gate.e_score_correction_bias", + "model.layers.66.post_attention_layernorm", + "model.layers.66.self_attn.indexer.k_norm", + "model.layers.66.self_attn.indexer.k_norm.bias", + "model.layers.66.self_attn.indexers_proj", + "model.layers.66.self_attn.kv_a_layernorm", + "model.layers.66.self_attn.q_a_layernorm", + "model.layers.67.input_layernorm", + "model.layers.67.mlp.gate", + "model.layers.67.mlp.gate.e_score_correction_bias", + "model.layers.67.post_attention_layernorm", + "model.layers.67.self_attn.indexer.k_norm", + "model.layers.67.self_attn.indexer.k_norm.bias", + "model.layers.67.self_attn.indexers_proj", + "model.layers.67.self_attn.kv_a_layernorm", + "model.layers.67.self_attn.q_a_layernorm", + "model.layers.68.input_layernorm", + "model.layers.68.mlp.gate", + "model.layers.68.mlp.gate.e_score_correction_bias", + "model.layers.68.post_attention_layernorm", + "model.layers.68.self_attn.indexer.k_norm", + "model.layers.68.self_attn.indexer.k_norm.bias", + "model.layers.68.self_attn.indexers_proj", + "model.layers.68.self_attn.kv_a_layernorm", + "model.layers.68.self_attn.q_a_layernorm", + "model.layers.69.input_layernorm", + "model.layers.69.mlp.gate", + "model.layers.69.mlp.gate.e_score_correction_bias", + "model.layers.69.post_attention_layernorm", + "model.layers.69.self_attn.indexer.k_norm", + "model.layers.69.self_attn.indexer.k_norm.bias", + "model.layers.69.self_attn.indexers_proj", + "model.layers.69.self_attn.kv_a_layernorm", + "model.layers.69.self_attn.q_a_layernorm", + "model.layers.70.input_layernorm", + "model.layers.70.mlp.gate", + "model.layers.70.mlp.gate.e_score_correction_bias", + "model.layers.70.post_attention_layernorm", + "model.layers.70.self_attn.indexer.k_norm", + "model.layers.70.self_attn.indexer.k_norm.bias", + "model.layers.70.self_attn.indexers_proj", + "model.layers.70.self_attn.kv_a_layernorm", + "model.layers.70.self_attn.q_a_layernorm", + "model.layers.71.input_layernorm", + "model.layers.71.mlp.gate", + "model.layers.71.mlp.gate.e_score_correction_bias", + "model.layers.71.post_attention_layernorm", + "model.layers.71.self_attn.indexer.k_norm", + "model.layers.71.self_attn.indexer.k_norm.bias", + "model.layers.71.self_attn.indexers_proj", + "model.layers.71.self_attn.kv_a_layernorm", + "model.layers.71.self_attn.q_a_layernorm", + "model.layers.72.input_layernorm", + "model.layers.72.mlp.gate", + "model.layers.72.mlp.gate.e_score_correction_bias", + "model.layers.72.post_attention_layernorm", + "model.layers.72.self_attn.indexer.k_norm", + "model.layers.72.self_attn.indexer.k_norm.bias", + "model.layers.72.self_attn.indexers_proj", + "model.layers.72.self_attn.kv_a_layernorm", + "model.layers.72.self_attn.q_a_layernorm", + "model.layers.73.input_layernorm", + "model.layers.73.mlp.gate", + "model.layers.73.mlp.gate.e_score_correction_bias", + "model.layers.73.post_attention_layernorm", + "model.layers.73.self_attn.indexer.k_norm", + "model.layers.73.self_attn.indexer.k_norm.bias", + "model.layers.73.self_attn.indexers_proj", + "model.layers.73.self_attn.kv_a_layernorm", + "model.layers.73.self_attn.q_a_layernorm", + "model.layers.74.input_layernorm", + "model.layers.74.mlp.gate", + "model.layers.74.mlp.gate.e_score_correction_bias", + "model.layers.74.post_attention_layernorm", + "model.layers.74.self_attn.indexer.k_norm", + "model.layers.74.self_attn.indexer.k_norm.bias", + "model.layers.74.self_attn.indexers_proj", + "model.layers.74.self_attn.kv_a_layernorm", + "model.layers.74.self_attn.q_a_layernorm", + "model.layers.75.input_layernorm", + "model.layers.75.mlp.gate", + "model.layers.75.mlp.gate.e_score_correction_bias", + "model.layers.75.post_attention_layernorm", + "model.layers.75.self_attn.indexer.k_norm", + "model.layers.75.self_attn.indexer.k_norm.bias", + "model.layers.75.self_attn.indexers_proj", + "model.layers.75.self_attn.kv_a_layernorm", + "model.layers.75.self_attn.q_a_layernorm", + "model.layers.76.input_layernorm", + "model.layers.76.mlp.gate", + "model.layers.76.mlp.gate.e_score_correction_bias", + "model.layers.76.post_attention_layernorm", + "model.layers.76.self_attn.indexer.k_norm", + "model.layers.76.self_attn.indexer.k_norm.bias", + "model.layers.76.self_attn.indexers_proj", + "model.layers.76.self_attn.kv_a_layernorm", + "model.layers.76.self_attn.q_a_layernorm", + "model.layers.77.input_layernorm", + "model.layers.77.mlp.gate", + "model.layers.77.mlp.gate.e_score_correction_bias", + "model.layers.77.post_attention_layernorm", + "model.layers.77.self_attn.indexer.k_norm", + "model.layers.77.self_attn.indexer.k_norm.bias", + "model.layers.77.self_attn.indexers_proj", + "model.layers.77.self_attn.kv_a_layernorm", + "model.layers.77.self_attn.q_a_layernorm", + "model.layers.78.eh_proj", + "model.layers.78.enorm", + "model.layers.78.hnorm", + "model.layers.78.input_layernorm", + "model.layers.78.mlp.gate", + "model.layers.78.mlp.gate.e_score_correction_bias", + "model.layers.78.post_attention_layernorm", + "model.layers.78.self_attn.indexer.k_norm", + "model.layers.78.self_attn.indexer.k_norm.bias", + "model.layers.78.self_attn.indexers_proj", + "model.layers.78.self_attn.kv_a_layernorm", + "model.layers.78.self_attn.q_a_layernorm", + "model.layers.78.shared_head.norm", + "model.norm" + ], + "quant_method": "fp8", + "weight_block_size": [ + 128, + 128 + ] + }, + "rms_norm_eps": 1e-05, + "rope_interleave": true, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "routed_scaling_factor": 2.5, + "scoring_func": "sigmoid", + "tie_word_embeddings": false, + "topk_group": 1, + "topk_method": "noaux_tc", + "transformers_version": "5.6.0.dev0", + "unsloth_fixed": true, + "use_cache": true, + "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..453800a061bdc65b75b9dd99ecc66ede543dac89 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "pad_token_id": 154820, + "temperature": 1.0, + "top_p": 0.95, + "transformers_version": "5.4.0" +} diff --git a/model-00001-of-00142.safetensors b/model-00001-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7e90e0a4f6e701b4ff07944034d726196ccdc01 --- /dev/null +++ b/model-00001-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205976fdd1cddd00be3bc1e20755a163054e225af995a72f6e4149c018204be4 +size 5363940952 diff --git a/model-00002-of-00142.safetensors b/model-00002-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b2d2ae9340471957f051f89894ca1206a5aacd4 --- /dev/null +++ b/model-00002-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d909a059ea5207282552fe5f5e4a4d411da68cf4644057ba1cc7a329ebfb2b9a +size 5361736696 diff --git a/model-00003-of-00142.safetensors b/model-00003-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c741fd78285d7bbdd74be6602a366c92a6771035 --- /dev/null +++ b/model-00003-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c708c55c71b2f537917ab7144ca1334f365724869662713439fe16e910582b +size 5363339120 diff --git a/model-00004-of-00142.safetensors b/model-00004-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8537ddabac41a3795da0debcff159075e95e10b8 --- /dev/null +++ b/model-00004-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8405236f949cd74c17af1d3ba65818f731e3dce4112a3760bb55ab808d86cae +size 5361736640 diff --git a/model-00005-of-00142.safetensors b/model-00005-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d02f375bae0c75707244b0612ab5a0623180c30a --- /dev/null +++ b/model-00005-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f76ae761b928c7e905748b3a5cb914528784ea0c6d4e8d84d3ebbd384998f62 +size 5363339176 diff --git a/model-00006-of-00142.safetensors b/model-00006-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c17f81439a80aeb5e6595e6253857be14c989b7 --- /dev/null +++ b/model-00006-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec9fcc3a36b3cd7df973960072f42b1e2fa93094cd9e798ea8b857ff9ba8bae +size 5361736504 diff --git a/model-00007-of-00142.safetensors b/model-00007-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c212cf0c289df3bc65460d46dd78d85c5122cf1a --- /dev/null +++ b/model-00007-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80205be2a99e07bc102228bf4b36b64d0ba1c175a75bd2905a83bbdd59bda06c +size 5363339304 diff --git a/model-00008-of-00142.safetensors b/model-00008-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..112301ca85b876f0dfea40dc44f762a0f10d37d2 --- /dev/null +++ b/model-00008-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3778a0c3bcaca60f56c44fbc4a87f60bfab72323bdf8f2cabd255ec7eb24ff7 +size 5361736368 diff --git a/model-00009-of-00142.safetensors b/model-00009-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6dbf362f70d0234045edcfb811bd4a29a6412f55 --- /dev/null +++ b/model-00009-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a4ad3a27c1863f32611e297b7ad85ddf229237d3aef3abff5895be59ef2ef4 +size 5363339440 diff --git a/model-00010-of-00142.safetensors b/model-00010-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f4baa748b2e187d7dfd8dc0dc082779a9d569f50 --- /dev/null +++ b/model-00010-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46449f548211661cb5c3845f16501b4250b9fae313914f9b83b31a365ed498d6 +size 5361736232 diff --git a/model-00011-of-00142.safetensors b/model-00011-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ea5e3ba7b1597b4a1b5e20e802b13644f6e49d1 --- /dev/null +++ b/model-00011-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36557532935d5edf38aef425de1494f51039f61b34d2f0a39aabf285bbfa7752 +size 5363339592 diff --git a/model-00012-of-00142.safetensors b/model-00012-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..914d079dcfe658d046083070097a12cca842639e --- /dev/null +++ b/model-00012-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c6ff15d39f1355bbda9802a595ef91262495f1d8381d8634bc2d7468d82509 +size 5363339104 diff --git a/model-00013-of-00142.safetensors b/model-00013-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..919a56f0a1cd41097211ddad80e1e98bfd6afe9f --- /dev/null +++ b/model-00013-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1722fbe67d4bfa26442617837f908445a272e269b26219791e7509e71f3041fb +size 5361736696 diff --git a/model-00014-of-00142.safetensors b/model-00014-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a4baa29bd46f559cfba2b47c6db5daf31902a6c --- /dev/null +++ b/model-00014-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4028b398d2e09e362dc360fa5fb536cafc80fa9326fd3a5f43a867cc937704 +size 5363339120 diff --git a/model-00015-of-00142.safetensors b/model-00015-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5171cbe83f98732137f02873f2ae95252a8f71c --- /dev/null +++ b/model-00015-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916305b18ec04fd399ec4f197bf29c7600df868f974327ead4280bd6c9004352 +size 5361736688 diff --git a/model-00016-of-00142.safetensors b/model-00016-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..675603373fdcfa217829fbb800c391aaa7e35d15 --- /dev/null +++ b/model-00016-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00444ce81f597e639561a3fa0126cdeaefc8122ae25bd14cce949b260861e554 +size 5363339128 diff --git a/model-00017-of-00142.safetensors b/model-00017-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..798563ea0ad56a217c1853ff24f3969961809b8f --- /dev/null +++ b/model-00017-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345af0570dc88a2ae4cceae6cd99e52ad6d149b619f49ee18bfce0aaad037838 +size 5361736552 diff --git a/model-00018-of-00142.safetensors b/model-00018-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..319d97d022402e8ac01437df4c709a5852dc86d6 --- /dev/null +++ b/model-00018-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69187f3011e235f55a47143b7b9998836acca7550e8924047e58b0f35ab6d554 +size 5363339256 diff --git a/model-00019-of-00142.safetensors b/model-00019-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b3584578c385c922bdea5a6a7d3f9015ef04d698 --- /dev/null +++ b/model-00019-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe4da41bf7287e53e77fa66ad7253b0189509b9fc964f00dffe77810c5fff19 +size 5361736416 diff --git a/model-00020-of-00142.safetensors b/model-00020-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c6181d3809a4563136e095e5e5de193c7eaa908 --- /dev/null +++ b/model-00020-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffbd31d3787cbb991c7026c263490206b84084f48f555fd1f5e5076ae75b1b5b +size 5361791448 diff --git a/model-00021-of-00142.safetensors b/model-00021-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cde8d8bf22464427d8f0f74d1488303b60c49928 --- /dev/null +++ b/model-00021-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da172eb3d7dcdb22196bef3e5d2f7997e27975007f32072c26e9b0cebdf3c27 +size 5361736352 diff --git a/model-00022-of-00142.safetensors b/model-00022-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eaafa17318b0e6fb9004d88e8cf123442424a414 --- /dev/null +++ b/model-00022-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8903dd5a119b301d23e37aa56b6c91b9c144b31d863a26af59177c9afab4dd +size 5363339456 diff --git a/model-00023-of-00142.safetensors b/model-00023-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..749ce3ce2b38c314d0f2353beb5e0a4211d5fa19 --- /dev/null +++ b/model-00023-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66c41ca799608fa422b382f31ea56d43b97872de552b1dada68a4d5ed6be1d28 +size 5361736224 diff --git a/model-00024-of-00142.safetensors b/model-00024-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd9465cb6ee924062ead3ef23bc055953b04300c --- /dev/null +++ b/model-00024-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8e543d1361c6504cf9f7cf937210cac1d7772c7f568bec5aac7f38e3e4aa30 +size 5363339608 diff --git a/model-00025-of-00142.safetensors b/model-00025-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c067a11b78492dd1aeebb307286830707c604dec --- /dev/null +++ b/model-00025-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4939a8045fc5619d72adf41d638107b2270845adc2862d8ec0cce349ded7c54c +size 5363339104 diff --git a/model-00026-of-00142.safetensors b/model-00026-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d9ae22db3eb471906c0d6f18a7d3768c3bd9134a --- /dev/null +++ b/model-00026-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ece8ece94c8e90d459951fc1e5acadbc744fb6c2fb06ceafa3ac3b829db25ab +size 5361736696 diff --git a/model-00027-of-00142.safetensors b/model-00027-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3213842d0e2be27fbf55c206566513cbcedfa84a --- /dev/null +++ b/model-00027-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad676bf742023e409af3722d70d097fc257991bdb0bd04bed8f17397b7def3c6 +size 5363339112 diff --git a/model-00028-of-00142.safetensors b/model-00028-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fff6cfc49384ffaa6122d35cfa5e1d417d9428c1 --- /dev/null +++ b/model-00028-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f37bad9f196213cd05081cf2d2a466f4dabaa22c594eff452933fcd5ab3dc64 +size 5361736664 diff --git a/model-00029-of-00142.safetensors b/model-00029-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a8190eeeedafecb38b82dc4a6342d261fcebe00 --- /dev/null +++ b/model-00029-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b49905f4405d2e7a70ca1b4af0851350c86e685f982a0570c600d11dd802880 +size 5363339152 diff --git a/model-00030-of-00142.safetensors b/model-00030-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff3ce9069759e853c25e1a478bf3a9762b5eae5a --- /dev/null +++ b/model-00030-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b654485f9c01c86621f6cb024e1f6bdd81300011b6b9b11275c3fa7982472d +size 5361736528 diff --git a/model-00031-of-00142.safetensors b/model-00031-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..02184f70dcb978c70d0558989f2779a06f45da89 --- /dev/null +++ b/model-00031-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d78a779bd69810b5cb6467dcaa8705c6a88d8c2e48e8408881ffd2dcbd4a46 +size 5363339280 diff --git a/model-00032-of-00142.safetensors b/model-00032-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8242f4034b83c2fcd10ed0948f413b40587163be --- /dev/null +++ b/model-00032-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995e8d62d59d3dc544864b1f3d64f43d698acb411bd9f001993437fe8ffc99bb +size 5361736392 diff --git a/model-00033-of-00142.safetensors b/model-00033-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..565670e96ac215ad193129f074752d730e1323d7 --- /dev/null +++ b/model-00033-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b8ed708b1c6c14283c378440bb687f71c2a4612ab35e910169a02e4678d6f7 +size 5363339416 diff --git a/model-00034-of-00142.safetensors b/model-00034-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2d30be2b538118a79d7cfb9831b58c7005889f8 --- /dev/null +++ b/model-00034-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d5253375958275caa3525b9a5a8bdca3a75cea15b98b36747fc4931777e7cc +size 5361736264 diff --git a/model-00035-of-00142.safetensors b/model-00035-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac175390b54ef2cd9c91a43099d8de65225ba3de --- /dev/null +++ b/model-00035-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a2d75e9d0598413de333185465867a1e1722441266a449c421e09a4b3bf813 +size 5363339544 diff --git a/model-00036-of-00142.safetensors b/model-00036-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ee4fb34d3e0ee85279c095a5814e58fa7f15399 --- /dev/null +++ b/model-00036-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441ae5c24d32a8b674dd8fb1db1d4835ef46bd470c9d2f096d86b5031a3fcb41 +size 5363339104 diff --git a/model-00037-of-00142.safetensors b/model-00037-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b3e1cb91e598bfca27f5515a5920e0dcc734d9a --- /dev/null +++ b/model-00037-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf844f6bee957fc203431c39b0a5eb9f104258c170e4e5490f1ea8487d593b6 +size 5361736696 diff --git a/model-00038-of-00142.safetensors b/model-00038-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d3d35b71b0e149018abe027d03deab1c42a9246 --- /dev/null +++ b/model-00038-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba412f5ccc524070eb35272438a2f549bb7165cb4b7b86530955bf281fe8ea2 +size 5363338920 diff --git a/model-00039-of-00142.safetensors b/model-00039-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac8757c7b5da629993d2607f7f1c01b50b2879e2 --- /dev/null +++ b/model-00039-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ebc73ae8cfce5ebcaf759962748d66b5010beccacd1f77b02e45d300c36c2b8 +size 5361735840 diff --git a/model-00040-of-00142.safetensors b/model-00040-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca5935b6e88caddfa99ebf3261f39b46d7343ec3 --- /dev/null +++ b/model-00040-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e6033cf198187e3a89fc90f6c9364712056b73669ba853e442a4bff812e695 +size 5363338584 diff --git a/model-00041-of-00142.safetensors b/model-00041-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d76316c61c4573de4400c79dbe94d36f005b4443 --- /dev/null +++ b/model-00041-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96b36ed04a5750c16a09df81f01cc396ca29bd7b50605990fcfab083b1d70c9 +size 5361736576 diff --git a/model-00042-of-00142.safetensors b/model-00042-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc871c050419073237cab13ba3f0353c6d2618f2 --- /dev/null +++ b/model-00042-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32899afc42f70a40d48640f15991f55a691ab04e49af60844cf476fb9e65ca9 +size 5363339232 diff --git a/model-00043-of-00142.safetensors b/model-00043-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19d5f9f3f374a334a3a7171371b5b309c1cce13f --- /dev/null +++ b/model-00043-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91036a2dbf0f882d0ca1a39db1e8735d40ba5e689f3cc06e0afb859cee5b288c +size 5361736440 diff --git a/model-00044-of-00142.safetensors b/model-00044-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95a70457fe7b0980e04445915e025f08d4e92495 --- /dev/null +++ b/model-00044-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7763ff9d8d8f85e0d9430a1688734744d5c5d4b46224f3b0cc555529f5d0a529 +size 5363339368 diff --git a/model-00045-of-00142.safetensors b/model-00045-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44d758f89e7e499af530fd41e0d93b45ff42e151 --- /dev/null +++ b/model-00045-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3e1fb4ed18f8fd9b3a89ececacbdfaa2af3b0f61a4550ebb6a31ce600b4b834 +size 5361736312 diff --git a/model-00046-of-00142.safetensors b/model-00046-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e67b9ddc0b7448cb83929a8a6efdf72ea493205 --- /dev/null +++ b/model-00046-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bcf2b2b8be75a1f7552bd0c164f6fd7973f8b5b77557cf657272b7080c4590b +size 5363339504 diff --git a/model-00047-of-00142.safetensors b/model-00047-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8266e38c1cd9753f42bdde1a72e856de3bd1177 --- /dev/null +++ b/model-00047-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f464b9c18529a519c45f2c15c668b472b8609f4d7ca1979b92a8c08480f8d434 +size 5342350104 diff --git a/model-00048-of-00142.safetensors b/model-00048-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..147e368edfbceed7fcc102d83ddfd19f9908a9bf --- /dev/null +++ b/model-00048-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e90eae66e53cddfd1552a5ddfd8bf79bf9e33b1914f67ba8871ba3f15831cd +size 5357553232 diff --git a/model-00049-of-00142.safetensors b/model-00049-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..562e09d7776d9581acb2488910a40ee627f7a57b --- /dev/null +++ b/model-00049-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25f7a4431fd3dcb43e7e8c9097112100db23319a2c1126f0003b9fcabc28a1b +size 5363339104 diff --git a/model-00050-of-00142.safetensors b/model-00050-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16ec787fe30235d41130871a2b70aebdd4fde1b2 --- /dev/null +++ b/model-00050-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79ea4649cecb0a980b77c0bac2a6e7232c60803ff64d880d35f4856d2ee9aee +size 5361736696 diff --git a/model-00051-of-00142.safetensors b/model-00051-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e25b499b9196fab120d4bd740161b6cb862cb6c --- /dev/null +++ b/model-00051-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26634691beece96dbe843e7017b012438f366ab3fed557bae907c1acadfe4f33 +size 5363339120 diff --git a/model-00052-of-00142.safetensors b/model-00052-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f531dcf6ba8474ed3cb597bfae48d7cc14b582e7 --- /dev/null +++ b/model-00052-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ed6313b28d80d1e6fcb3ca0fbd26a0a2a75f86e3160aca543802941449b04c +size 5361736632 diff --git a/model-00053-of-00142.safetensors b/model-00053-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a91c0caddecf1c35a2eacfedd0fa692fe5dd247 --- /dev/null +++ b/model-00053-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c4edd555eb0f500955c8820fbcf01f03d080da1f747d4227db73a4ce637cea +size 5363339176 diff --git a/model-00054-of-00142.safetensors b/model-00054-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e3862fcd39c39887b94482e63aca4ed7c85d0f16 --- /dev/null +++ b/model-00054-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc34d07e8b48f9ac2b761044915ce1c54c904b1cf8830d4f89c99c27743c0962 +size 5361736496 diff --git a/model-00055-of-00142.safetensors b/model-00055-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd7690536bce449c1594d66dabfb7ff079eb85b5 --- /dev/null +++ b/model-00055-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31f426911d19731e6f7052c58c7ef36506b509b689934d3a5a9366147949155 +size 5363339320 diff --git a/model-00056-of-00142.safetensors b/model-00056-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6838f4f7c063b71cbd79e7b2798cf60a74863814 --- /dev/null +++ b/model-00056-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8b17b5669adaf23464dbce9871a9240c7e811d0142979952ef4d7d1bfeaf7b +size 5361736360 diff --git a/model-00057-of-00142.safetensors b/model-00057-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..270b31265880e4b653f960eb9e5234ba5fe73598 --- /dev/null +++ b/model-00057-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a3eda892b07bca6d281c2892c8e0afa9d3cd372bbadb7a32ea53c867c31f04 +size 5363339448 diff --git a/model-00058-of-00142.safetensors b/model-00058-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa56ad207add4a86470a73e30f885e7d34142738 --- /dev/null +++ b/model-00058-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dacb2505271a4f1429ccb04b4d220d2b574f1beda79c2c1544fd34788149318 +size 5361736224 diff --git a/model-00059-of-00142.safetensors b/model-00059-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8e2739fdead7b28a727ee4611559f8751b24327 --- /dev/null +++ b/model-00059-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de72a77ea958ec1cb91f8a9e0adf0248fbb5646c390dc591c8cfeb6f08121d1 +size 5363338800 diff --git a/model-00060-of-00142.safetensors b/model-00060-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb115ec1d8d7b30163812d61f0d4dd14989c4dd0 --- /dev/null +++ b/model-00060-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0430b0f5b1b2381a8f6002ed5f16a0a8a46ffde2690fda4113e776d3d71b014 +size 5363338336 diff --git a/model-00061-of-00142.safetensors b/model-00061-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce9ab5da4db7a2f562c8a34253624b0a3579a8c5 --- /dev/null +++ b/model-00061-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53485d2cb922ac2a4d4e9936c50683448739e2a5cb9b3cf9c57e60498a3bae9 +size 5361736696 diff --git a/model-00062-of-00142.safetensors b/model-00062-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f0f2bffc0074769bad8ce4306c7e300d7ab7711 --- /dev/null +++ b/model-00062-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5432981d1b2516aa93c8506bb59721cdb3c6dbdb5095eb32804d06e90ffd485 +size 5363339112 diff --git a/model-00063-of-00142.safetensors b/model-00063-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d63f569b9fe4013373693c14aba55c5bc70cb11 --- /dev/null +++ b/model-00063-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:108c6e36bd436874a1be0d84657e5964231a53b2acf41b9f5885123e3d0f754a +size 5361736680 diff --git a/model-00064-of-00142.safetensors b/model-00064-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aee02dc281cead3224ac61fb29ccdb3f27387e07 --- /dev/null +++ b/model-00064-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335a18eb4faa9a2e4b0c0425d75322b47f7b9808ca48a9c03dce6bde87816942 +size 5363339128 diff --git a/model-00065-of-00142.safetensors b/model-00065-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a903bd491090396b0561fb32cd1015412cb701f2 --- /dev/null +++ b/model-00065-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa1fcc2ba6c7f7439777362590c65c048c4211dbb6f01b462d047b0fbe97591 +size 5361736552 diff --git a/model-00066-of-00142.safetensors b/model-00066-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a05fe622f0841d0d4b4c31272ba2c9484e2fa68 --- /dev/null +++ b/model-00066-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e85116f997e723fc023800b3d600ad07873bb5ee23a50ee088a099d0e958aa83 +size 5363339264 diff --git a/model-00067-of-00142.safetensors b/model-00067-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c293b80737ca2cb30e7974d3f314ab3fae64625 --- /dev/null +++ b/model-00067-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed2d941d5c2dc603e4c80bae92aa8845a8b5b605526da829ed7ab48f7021142 +size 5361736416 diff --git a/model-00068-of-00142.safetensors b/model-00068-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7df95ed9ac31e477277c6ac7fa5009365aac458 --- /dev/null +++ b/model-00068-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e846e559c9a26f01f44ddfcfa8f433d55a637e530a8f298d95dd357220ec48d7 +size 5363339400 diff --git a/model-00069-of-00142.safetensors b/model-00069-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1f1024344cf1ae2f7e6db0b398b5e984ac180e1 --- /dev/null +++ b/model-00069-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907b38c71f3345fa14fad3fc94b5a27b32d0fb77369c2bf916075b42730ad73d +size 5361736280 diff --git a/model-00070-of-00142.safetensors b/model-00070-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ef2cc8407db040c6f9fd69432d4833d5977a350 --- /dev/null +++ b/model-00070-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc0fa844bc418f51bf62b777a56f1f95b94b1b2d93308ff014e80aa591b7e42 +size 5363339528 diff --git a/model-00071-of-00142.safetensors b/model-00071-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9806c74c6b2fce004aba6619703f44f6d6dd34bf --- /dev/null +++ b/model-00071-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ccdeb511e70cdfd729f4a8ebb55ef9c54a72d9e52c5bd16a92666aea921456 +size 5363339104 diff --git a/model-00072-of-00142.safetensors b/model-00072-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..039d0aec57e9f5c0bf2c4d4dfe369a656d60b90c --- /dev/null +++ b/model-00072-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6408c8c9a09d9dc4264e1984bc3add92281270c731f64d91a0d96bb6391e119e +size 5361736696 diff --git a/model-00073-of-00142.safetensors b/model-00073-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44a0bc550630ff9cb65970e300e8e243cdda17ca --- /dev/null +++ b/model-00073-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c4eb8ed0dd56eebb81a0d44f6570e758e561a86cd29645024ee8c3c074690f +size 5363339104 diff --git a/model-00074-of-00142.safetensors b/model-00074-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d5413f3d14bdd436b6e5d844ffb680e952b150a --- /dev/null +++ b/model-00074-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:978db2195765b2259f71de6583d59f859091570bfaa8f548cf775e99396dd535 +size 5361736696 diff --git a/model-00075-of-00142.safetensors b/model-00075-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04a579c0561db26244c8f77c567f0ff2a0264a0d --- /dev/null +++ b/model-00075-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee63e9bb88509ab0089756e68a80795558a5a2fa2d19c631b66835955197d4da +size 5363339112 diff --git a/model-00076-of-00142.safetensors b/model-00076-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36851d0227e9cf3f56c5df7f54c7aedc0e88bb6f --- /dev/null +++ b/model-00076-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7df10590ad98767b7c412c550c0debf8943de696d2acc422553e55945a52dd7f +size 5361736592 diff --git a/model-00077-of-00142.safetensors b/model-00077-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3478fbaf35951f5b8b9baa65d162d11ae29e50b6 --- /dev/null +++ b/model-00077-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb120541f2f25a39fd8e4b592492a365658bad9d460dabbb41e55346b0542e47 +size 5363339224 diff --git a/model-00078-of-00142.safetensors b/model-00078-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d06c82eeba11d25518f72f50d387d2a3e829344d --- /dev/null +++ b/model-00078-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed29e4169e21d333cae9f47dc66760a8030ec4d8274b8ad17b28fef03a001ea +size 5361736456 diff --git a/model-00079-of-00142.safetensors b/model-00079-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb75da9ae96c946250e6584c3f9b5ed2dd291799 --- /dev/null +++ b/model-00079-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e4dfa5e801ffeb773671f187a981b4e7454a47006f733181a446fc381803cb +size 5363338784 diff --git a/model-00080-of-00142.safetensors b/model-00080-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0bc3e9dd62c36e9e09ef1886a47f08a222e48d83 --- /dev/null +++ b/model-00080-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92f502b1234c8909dcd7d20ef558bda611a8989ab00f71a306a260767661a0b +size 5361735472 diff --git a/model-00081-of-00142.safetensors b/model-00081-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9dff3580cc0c58d6c5266945bc6f6216253e897c --- /dev/null +++ b/model-00081-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fafe2068fcc0ec959cb44ceb11f3e8f2caf00e76b1725ff18daeaf84e07ac70 +size 5363339344 diff --git a/model-00082-of-00142.safetensors b/model-00082-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e9753633bdf49ffaa82a7ac9a3661f80d98979b --- /dev/null +++ b/model-00082-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a6351865a588d7d68852952637df7c1cd429ffd60979717dd91acb5ed8663d2 +size 5317175232 diff --git a/model-00083-of-00142.safetensors b/model-00083-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e54327f506689fa546f78dbc09b8b3d257a17fb8 --- /dev/null +++ b/model-00083-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981c0ae29f9c0b0c49488e689688028105e5c6a90e00b78e98d7fd82d077c1b8 +size 5357555688 diff --git a/model-00084-of-00142.safetensors b/model-00084-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7d322e1ebbb2b5738f09bb63fcb024e3323603d --- /dev/null +++ b/model-00084-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da16d8b9f80d7c8bf7cf120509b90fc0ea38c932614e392a1ac2d4dddccff2ec +size 5363339104 diff --git a/model-00085-of-00142.safetensors b/model-00085-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e640df17f03b397eab9892a7af8c08e3bef79b0 --- /dev/null +++ b/model-00085-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d03bb770e771d2754f25d93e5d0d1f38899a8169b3d4335fd1a26344ec4a522 +size 5361736696 diff --git a/model-00086-of-00142.safetensors b/model-00086-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54f5e7d90d6f22da7271afec8b617726b1513c3f --- /dev/null +++ b/model-00086-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80724e44554a5eaa5f7266cd0fe3d3b3930066399d69a5f3ede191e7abb61342 +size 5363339120 diff --git a/model-00087-of-00142.safetensors b/model-00087-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..373f4c73dbc52e47ba9694ccfdb2d930f512ddf6 --- /dev/null +++ b/model-00087-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d2aee9f1d403c781706479fc15393c9d50ba021acaac371bda7436981171643 +size 5361736648 diff --git a/model-00088-of-00142.safetensors b/model-00088-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2a6a5355589549282d17d8520d3ab16a96323bf --- /dev/null +++ b/model-00088-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed2ce0f76905fad2b235aa5958b3e38d2b2d247b3248462edd6bec012e5f2af +size 5363339160 diff --git a/model-00089-of-00142.safetensors b/model-00089-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59fb67622b2534268dd5110788e18f78d065e59b --- /dev/null +++ b/model-00089-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc8f74f5d1c59f7ae59b781db77b9e5b6b14e3afff606577ed7a022c9099f772 +size 5361736512 diff --git a/model-00090-of-00142.safetensors b/model-00090-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35df3646e4ece72b50f5e36f4d73498fff0a74f5 --- /dev/null +++ b/model-00090-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b7c55a3afd2437114230c43ed055115d13f813d9842856c631ee83f2bc75ca +size 5363339296 diff --git a/model-00091-of-00142.safetensors b/model-00091-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50d2cac84b4cd94b83fe646527e0cb5db4e2b155 --- /dev/null +++ b/model-00091-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ba80b3e2bc846d818acc34086f268edd3220e824b65cfaf39e9de78e0efcff +size 5361736376 diff --git a/model-00092-of-00142.safetensors b/model-00092-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32e45b4532e9ce03b1b7894c49a93a2c1bc32268 --- /dev/null +++ b/model-00092-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7b665e99148cabc64b083120befb34ce3bb6bdb3be076796fc1e387332bfec +size 5363339432 diff --git a/model-00093-of-00142.safetensors b/model-00093-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5884d7d5fd0195de5745fe4c26faea8ce22fdc67 --- /dev/null +++ b/model-00093-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8cf02a6a1d2ce2a277b7f7e412f50c83208a06db8b7b36098d61cbb030909b6 +size 5361736248 diff --git a/model-00094-of-00142.safetensors b/model-00094-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24b13a664d0d77b66f95432baa1547d4fd2926bb --- /dev/null +++ b/model-00094-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad65481085844f604e45a2062124d7136a34f656ed08d91c7e9d367c8a1a8be2 +size 5363339576 diff --git a/model-00095-of-00142.safetensors b/model-00095-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ed19af12bc9c5227b3d55df50aece4941576b3a --- /dev/null +++ b/model-00095-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1373ea4325b07ed30e871d92ae31a4d6f413a0f5aedf42cfb6ef280d58ea2647 +size 5363339104 diff --git a/model-00096-of-00142.safetensors b/model-00096-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94cf15dd9e8a67c72d66e4a981caba107d9a5076 --- /dev/null +++ b/model-00096-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec77fa04a9ae727212106274fbac1c783ad0e40a446064fd20fb5ebc91f97dce +size 5361736696 diff --git a/model-00097-of-00142.safetensors b/model-00097-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8e29484ff118e6d97baff2dd1fe274dcdc6aad4 --- /dev/null +++ b/model-00097-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed15272340c1d88dc8ed31615fe739d31bde94285ce376adab69eebab617893d +size 5363339120 diff --git a/model-00098-of-00142.safetensors b/model-00098-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..09eaa40794c8c5ed8d37fb9a3cfdfb4c9c8e1ab2 --- /dev/null +++ b/model-00098-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30bad76ba7422cba887b828324b40b2aa045cdef9d88584318d3f5896603b09 +size 5361736696 diff --git a/model-00099-of-00142.safetensors b/model-00099-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e076a5514b52726bdb937186f009e5ddc7fecd5e --- /dev/null +++ b/model-00099-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b64e2913fef5c20490e41f5b48c09de50bd810def10eb31b73a73eb82eadae97 +size 5363338784 diff --git a/model-00100-of-00142.safetensors b/model-00100-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ea190e700a03096838e8fc80a7f7632763498f8 --- /dev/null +++ b/model-00100-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f3901b64d28af66a091c950edd784e0abaaada4220632494204fee8bb7a7257 +size 5361735712 diff --git a/model-00101-of-00142.safetensors b/model-00101-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94052530fa05f027a37f0423b7df44885a33644a --- /dev/null +++ b/model-00101-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8b320af495b1f8b203e0de3cca19abf78db0936db7b7113fbf6d1236049b754 +size 5363338872 diff --git a/model-00102-of-00142.safetensors b/model-00102-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dde536df4e054cf463e8987db67ff53d832e810d --- /dev/null +++ b/model-00102-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873e97c71b26deb73b1767b2b31f61477a1f48a15c6866025990465a84dbaa2f +size 5361736424 diff --git a/model-00103-of-00142.safetensors b/model-00103-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec60c6e8e3b43f9a3a97e50b016f56309bd3b6ae --- /dev/null +++ b/model-00103-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e76012a962bcac8301a9a81af5a5acd2284085814ddab24c9a2c511cbf82fbd +size 5363339384 diff --git a/model-00104-of-00142.safetensors b/model-00104-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27a4af91ac9a8db3cd1049b22ac9aa97d0ba9c47 --- /dev/null +++ b/model-00104-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73dbfe8a8d96453413bb6ad94fb255e66dbe3d59502ebb38f5cddb968501946 +size 5361736296 diff --git a/model-00105-of-00142.safetensors b/model-00105-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb871a0d7d289fc2ae3d2658a2b2c3e153306682 --- /dev/null +++ b/model-00105-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a954d9068edef54cd27e627cccaa3b09cff9b3b58e3519b3fbef823f9a4ab14 +size 5363339520 diff --git a/model-00106-of-00142.safetensors b/model-00106-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39a320b780ba5f93aa248abfe1cdf413d8fa18b4 --- /dev/null +++ b/model-00106-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b741d263cc5105391c6a9d8ddc9c320148dd291fd119e8f3d145265306fc9bf +size 5363339104 diff --git a/model-00107-of-00142.safetensors b/model-00107-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aef9e81ddf4a5a7e5efc5aa9f17c5a32f17be2a6 --- /dev/null +++ b/model-00107-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8a18b196255838ecc3c996690a933cc274794390cfebd7368cca7b80d564da +size 5361736696 diff --git a/model-00108-of-00142.safetensors b/model-00108-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..446b95abd1d3f14b0cd5a0930c615ee0b973391f --- /dev/null +++ b/model-00108-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67484855cd50dda6304040c4513cfe8af6d1b927e97e222ded9160e9e184fd14 +size 5363339104 diff --git a/model-00109-of-00142.safetensors b/model-00109-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a165a4f551300de53843f8e5a584fe9e2a8094b0 --- /dev/null +++ b/model-00109-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f5038fc9785c8dee01b19ad9e1322164cf54830398a247b631a8743ce3f575 +size 5361736696 diff --git a/model-00110-of-00142.safetensors b/model-00110-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b10ccd8f421ddb5886e0bbc2beee7823b7a7de0c --- /dev/null +++ b/model-00110-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18671e2f94f58f2ec04fde2a9ffcc69a0067ed5f9e0c2ea53a5da4546516dc26 +size 5363339112 diff --git a/model-00111-of-00142.safetensors b/model-00111-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d2db650ef080503443343ccea358b7be03d6a58 --- /dev/null +++ b/model-00111-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5928d158a1c5f6397417379fc97fc9f3dd70153787724e427e72432caff5f5 +size 5361736616 diff --git a/model-00112-of-00142.safetensors b/model-00112-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54b10dcd7fe824a7a376b8ba7b796e5d581d6e07 --- /dev/null +++ b/model-00112-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c451b30d06b64be28bf4d32883f3cefe7a561d6b7623834c58276dc647c344 +size 5363339200 diff --git a/model-00113-of-00142.safetensors b/model-00113-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d063877b1a0d10fa82f76935b465a30d8985acf --- /dev/null +++ b/model-00113-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6352977f557e3cd8bc7507df15fd625a1714120897e08b00d819656db017c0bb +size 5361736480 diff --git a/model-00114-of-00142.safetensors b/model-00114-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e4c4e069cfd0d1c1b0b8fa27ff371f0a6ebce7bf --- /dev/null +++ b/model-00114-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd83b52ac8f08738f5fa8e2c74ce16033946bcc262d2458049254e76ea5f2d9 +size 5363339328 diff --git a/model-00115-of-00142.safetensors b/model-00115-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2c3ace852bb06e716e9d041ee95cb5265bebb6b --- /dev/null +++ b/model-00115-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314fc05e8699bccd5420806525620ffad96d4cf6e085613f3718afdbfc715d47 +size 5361736344 diff --git a/model-00116-of-00142.safetensors b/model-00116-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ce61a5debadacfc9e6241d0fbfe17eed670150c --- /dev/null +++ b/model-00116-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053efffafb9bc63e45fb5f31b0ca2be4ab32a44fa4d290a8367e8a55ada2da4c +size 5363339456 diff --git a/model-00117-of-00142.safetensors b/model-00117-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ebaa4475b159f683f31a66b12290bc54b5d794f --- /dev/null +++ b/model-00117-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7ecc4f974fe76113a32c68f3b0d4c5139025114dad01f1982e155aaf2d3605 +size 5364883192 diff --git a/model-00118-of-00142.safetensors b/model-00118-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..130bf37aac0bda7b903d56b4e9c9bc8bb2fe4146 --- /dev/null +++ b/model-00118-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55cead6933f98f1044d2706fea44837066676d7e179fe18772c07316593b13d9 +size 5360192648 diff --git a/model-00119-of-00142.safetensors b/model-00119-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b02e842d7873a037b702249a58ec9303eb43936a --- /dev/null +++ b/model-00119-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437b5164ef8bffc0c477c239fbccc4b813f206ca5984104fa3a8207f4625e9ed +size 5363339008 diff --git a/model-00120-of-00142.safetensors b/model-00120-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a00b04aca1f7d8f0dc9c42efab0832f0998d647 --- /dev/null +++ b/model-00120-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23b49900d74f63554c61be9dadb5946903e00bb852081fba77b26d77af064ac8 +size 5361735840 diff --git a/model-00121-of-00142.safetensors b/model-00121-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c68909272673fe47c7f3cbdc946c26b77a3eca7 --- /dev/null +++ b/model-00121-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51afac838d8e84927ce68eaadcbe4273606f69094e29a762ccebc35be2c8c681 +size 5363338504 diff --git a/model-00122-of-00142.safetensors b/model-00122-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45ee771773dc40401293dfe4a1200f26d569a905 --- /dev/null +++ b/model-00122-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d735a8b726c38fef009c766e2fcc89f328bf9d468c0335fb57847959631523c0 +size 5361736656 diff --git a/model-00123-of-00142.safetensors b/model-00123-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a360fb7774c738d131e5d5302fffbc3c04afed4 --- /dev/null +++ b/model-00123-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba6b15e37307b72dfb1343baab5d5469708f9ac48603439bcedf05a8bd4c81b +size 5363339152 diff --git a/model-00124-of-00142.safetensors b/model-00124-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac99db8bc52b0adcf48e27b1d307262fd3b3ba64 --- /dev/null +++ b/model-00124-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4f759a35ccab24d6b3e8e7b549cfe0e720828ed31cb909847fde2755df0627 +size 5361736520 diff --git a/model-00125-of-00142.safetensors b/model-00125-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6dcc06a3161b12a610e66f3bd6ecfeb6ca5dc22d --- /dev/null +++ b/model-00125-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe518d2a1936ad6b2a7aa4f0b6dbd7452822261be7d1e063754410e0796147b +size 5363339288 diff --git a/model-00126-of-00142.safetensors b/model-00126-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..946965319a433224a2c0cc1a7bbfc932a13653e1 --- /dev/null +++ b/model-00126-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d00348fc44eb54efd8e3e1705ddb9e76113bf8ccc4de13b2d76f4ade8e3155a +size 5361736392 diff --git a/model-00127-of-00142.safetensors b/model-00127-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbd08d859bb4d9632d94615e143dcadd8505943e --- /dev/null +++ b/model-00127-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf652a702fa2d8c662a066d0a5bee79549d17882ab272cb74e3e4e03d44335bc +size 5363339416 diff --git a/model-00128-of-00142.safetensors b/model-00128-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8166cd88a3cad39411acf520dc801d678e4eade3 --- /dev/null +++ b/model-00128-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61db42ba6631fdb07d819c120ff9f61f4ff69efd018e094ef3c2376b38033f06 +size 5361736256 diff --git a/model-00129-of-00142.safetensors b/model-00129-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef386324cc41fce3a71979ec4085ab506c47ab08 --- /dev/null +++ b/model-00129-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72dd93b904c074a6908fb89aec499c7e1707924a9f55e5dc5223d640d86752fe +size 5363339560 diff --git a/model-00130-of-00142.safetensors b/model-00130-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7b375bc095e4e020f9a42bf32cbd9f211972c6f --- /dev/null +++ b/model-00130-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e962ce71a2e0dd5232265843fadee064e961b2fa290b5ae3f1e82128f11ca6f2 +size 5363339104 diff --git a/model-00131-of-00142.safetensors b/model-00131-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4df74c5cab3144811599d6392de150c914c7f75f --- /dev/null +++ b/model-00131-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc16ccebde523df12e57d3e49514d86073564326d1a75f6c5b929ec557520e3 +size 5361736696 diff --git a/model-00132-of-00142.safetensors b/model-00132-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5ad95278b96c7f6880fa7248028ac4ffa7343c5 --- /dev/null +++ b/model-00132-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30285d669521cd0ad2a17b0e9d142c86624c364947cb15fec8e5677ab493301 +size 5363339104 diff --git a/model-00133-of-00142.safetensors b/model-00133-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1e158e0c0d8f27944a3b22e7b23ec4e7ebec485 --- /dev/null +++ b/model-00133-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e604cc4a28638f58d0e19332838bf019c4f649981c94dc0110155ca2ef536ab9 +size 5361736696 diff --git a/model-00134-of-00142.safetensors b/model-00134-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b851c61ae4df230bf20a71cc17c6d07deaf15bb3 --- /dev/null +++ b/model-00134-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f2497a9b0ff1be584fb8367d240ae48d774e39712b29150726e18a740bda9b +size 5363339120 diff --git a/model-00135-of-00142.safetensors b/model-00135-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85f86806f8b83bcd5c758208642ab3fc113874d1 --- /dev/null +++ b/model-00135-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f35babc4edd3a78d04a0f6a018ccdecc5c7f9f5d147cb26a0f15c0bb151ee71d +size 5361736568 diff --git a/model-00136-of-00142.safetensors b/model-00136-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2565bcaff759bfa1700ac6b4b1d6f72608cb815 --- /dev/null +++ b/model-00136-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:705bd4c571863f08e9d6c2e40bca87add686764de0af40dd2eb36889f150a150 +size 5363324248 diff --git a/model-00137-of-00142.safetensors b/model-00137-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98ef91bcd7189d42f724404f8630bebbc66bc57b --- /dev/null +++ b/model-00137-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e802972d6ad81a10fb18cbf054834c1700aa2d67e025116c8451036d5a70b8db +size 5361736464 diff --git a/model-00138-of-00142.safetensors b/model-00138-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d6bbc83c150135461e3580e6f9cbb0526b6e676a --- /dev/null +++ b/model-00138-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37ce395ff4d5e7e2e57283e0bf5633c5bd867b87d0a874b2e5e604a9200bc22 +size 5363351176 diff --git a/model-00139-of-00142.safetensors b/model-00139-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15ad43a90bdb1c56fe2a5ea7452d4830da04fe9d --- /dev/null +++ b/model-00139-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:862e5ebd79fdbfd1406a227740efd5e7d55090afddd66c2a660285bbd496a534 +size 5361735472 diff --git a/model-00140-of-00142.safetensors b/model-00140-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c65e78434b02616ad5a0bb818e1ef4a15c05aad --- /dev/null +++ b/model-00140-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c013efa52322d2e9d3033987df200c89420b5c1124b52568497f67de21d7287 +size 5363338640 diff --git a/model-00141-of-00142.safetensors b/model-00141-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69754c47086d445b7a9aff2bccd15d6c8ec4ab90 --- /dev/null +++ b/model-00141-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba01737a521b4edd93b51b966730b12fcc609b3fff7cae776b195a847f87431 +size 5342346848 diff --git a/model-00142-of-00142.safetensors b/model-00142-of-00142.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..332dac3ae29a5201ff9b76d470797653c6c22506 --- /dev/null +++ b/model-00142-of-00142.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f1a5ce91c5fc330725bfca39aa63ba6f72eb02daaa85ed2ee4bfa7f00d0e5d +size 146853760 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b462c0bcd8028c8c87650fa6d00cda11cd585c5b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5c43b9fd27c3ba067265426673431c9cc747d8a5b27e1dab9df9c0fd575e371 +size 11396202 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..50ef91a5c0e787b36a059d8f3c85fb9e9456a5dc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,36 @@ +{ + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>" + ], + "is_local": true, + "model_max_length": 202752, + "model_specific_special_tokens": {}, + "pad_token": "[MASK]", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "TokenizersBackend", + "unk_token": null, + "chat_template": "[gMASK]\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n {%- if k != 'defer_loading' and k != 'strict' -%}\n {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n {%- set ns_tool.first = false -%}\n \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n {%- endif -%}\n {%- endfor -%}\n {{- '}' -}}\n{%- endmacro -%}\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{%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\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, thinking_indices='') -%}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- elif m.role == 'assistant' %}\n {%- if m.reasoning_content is string %}\n {%- set ns.thinking_indices = ns.thinking_indices ~ ',' ~ ns.last_user_index ~ ',' -%}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- set ns.has_thinking = false -%}\n{%- for m in messages -%}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}{% set ns.has_thinking = (',' ~ loop.index0 ~ ',') in ns.thinking_indices -%}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- elif '' in content %}\n {%- set reasoning_content = content.split('')[0].split('')[-1] %}\n {%- set content = content.split('')[-1] %}\n{%- elif loop.index0 > ns.last_user_index and not (enable_thinking is defined and not enable_thinking) %}\n {%- set reasoning_content = '' %}\n{%- elif loop.index0 < ns.last_user_index and ns.has_thinking %}\n {%- set reasoning_content = '' %}\n{%- endif %}\n{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '' + reasoning_content + ''}}\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 loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' -}}\n{%- endif %}\n{%- if m.content is string -%}\n {{- '' + m.content + '' -}}\n{%- else -%}\n {{- '\\n' -}}\n {% for tr in m.content %}\n {%- for tool in tools -%}\n {%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n {%- endif -%}\n {%- if tool.name == tr.name -%}\n {{- tool_to_json(tool) + '\\n' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {{- '' -}}\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