diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..aa7aacd0134a92c3c1943fdecc75cd8b7420cce6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/.mdl b/.mdl new file mode 100644 index 0000000000000000000000000000000000000000..3b940d405e39dff8d36da2a61cd1dbf197f51cc4 Binary files /dev/null and b/.mdl differ diff --git a/.msc b/.msc new file mode 100644 index 0000000000000000000000000000000000000000..706d9786519e92dc694820305a377a2a76d8350e Binary files /dev/null and b/.msc differ diff --git a/.mv b/.mv new file mode 100644 index 0000000000000000000000000000000000000000..0beb780a4ddfc8fc98024520db2e86d497d9594f --- /dev/null +++ b/.mv @@ -0,0 +1 @@ +Revision:master,CreatedAt:1753860431 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ee29a19f89eccf7eeda5be2f5406140edff91ebc --- /dev/null +++ b/README.md @@ -0,0 +1,104 @@ +--- +library_name: transformers +pipeline_tag: text-generation +tags: +- glm4_moe +- GPTQ +- Int4-Int8Mix +- 量化修复 +- vLLM +base_model: + - ZhipuAI/GLM-4.5 +base_model_relation: quantized +--- +# GLM-4.5-GPTQ-Int4-Int8Mix +基础型 [ZhipuAI/GLM-4.5](https://www.modelscope.cn/models/ZhipuAI/GLM-4.5) + + +### 【Vllm 单机8卡启动命令】 +注: 8卡启动该模型一定要跟`--enable-expert-parallel` ，否则其专家张量TP整除除不尽；4卡则不需要。 +``` +CONTEXT_LENGTH=32768 + +vllm serve \ + tclf90/GLM-4.5-GPTQ-Int4-Int8Mix \ + --served-model-name GLM-4.5-GPTQ-Int4-Int8Mix \ + --enable-expert-parallel \ + --swap-space 16 \ + --max-num-seqs 512 \ + --max-model-len $CONTEXT_LENGTH \ + --max-seq-len-to-capture $CONTEXT_LENGTH \ + --gpu-memory-utilization 0.9 \ + --tensor-parallel-size 8 \ + --trust-remote-code \ + --disable-log-requests \ + --host 0.0.0.0 \ + --port 8000 +``` + +### 【依赖】 + +``` +vllm==0.10.0 +``` + +### 【模型更新日期】 +``` +2025-07-30 +1. 首次commit +``` + +### 【模型列表】 + +| 文件大小 | 最近更新时间 | +|---------|--------------| +| `192GB` | `2025-07-30` | + + + +### 【模型下载】 + +```python +from modelscope import snapshot_download +snapshot_download('tclf90/GLM-4.5-GPTQ-Int4-Int8Mix', cache_dir="本地路径") +``` + + +### 【介绍】 +# GLM-4.5 + +
+ +
+

+ 👋 加入我们的 微信群 。 +
+ 📖 查看GLM-4.5 技术博客 。 +
+ 📍 在 智谱AI开放平台 上使用GLM-4.5 API服务。 +
+ 👉 一键体验 GLM-4.5 。 +

+ +## 模型介绍 + +**GLM-4.5** 系列模型是专为智能体设计的基础模型。GLM-4.5拥有 **3550** 亿总参数量，其中 **320** 亿活跃参数；GLM-4.5-Air采用更紧凑的设计，拥有 + **1060** 亿总参数量，其中 **120** 亿活跃参数。GLM-4.5模型统一了推理、编码和智能体能力，以满足智能体应用的复杂需求。 + +GLM-4.5 和 GLM-4.5-Air 都是混合推理模型，提供两种模式：用于复杂推理和工具使用的思考模式，以及用于即时响应的非思考模式。 + +我们已开源了 GLM-4.5 和 GLM-4.5-Air 的基础模型、混合推理模型以及混合推理模型的FP8版本。它们采用MIT开源许可证发布，可用于商业用途和二次开发。 + +在我们对12项行业标准基准的全面评估中，GLM-4.5表现卓越，得分 **63.2**，在所有专有和开源模型中排名**第3** +。值得注意的是，GLM-4.5-Air在保持优异效率的同时，仍取得了 **59.8** 的竞争性成绩。 + +![bench](https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/bench.png) + +如需了解更多评估结果、展示案例和技术细节，请访问我们的 [技术博客](https://z.ai/blog/glm-4.5)。技术报告将很快发布。 + +模型代码、工具解析器和推理解析器可在 [transformers](https://github.com/huggingface/transformers/tree/main/src/transformers/models/glm4_moe)、 [vLLM](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/glm4_moe_mtp.py) +和 [SGLang](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/glm4_moe.py) 的实现中找到。 + +## 快速开始 + +请参考我们的[github](https://github.com/zai-org/GLM-4.5)项目。 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..41478957aca7a04b7321022e7d1f73de5badd995 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{{ visible_text(m.content) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson(ensure_ascii=False) if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '\n' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..32979fc8b1bb39c34a48593b8054955a92288492 --- /dev/null +++ b/config.json @@ -0,0 +1,60 @@ +{ + "name_or_path": "tclf90/GLM-4.5-GPTQ-Int4-Int8Mix", + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "pad_token_id": 151329, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "partial_rotary_factor": 0.5, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1536, + "norm_topk_prob": true, + "num_attention_heads": 96, + "n_group": 1, + "topk_group": 1, + "n_routed_experts": 160, + "n_shared_experts": 1, + "routed_scaling_factor": 2.5, + "num_experts_per_tok": 8, + "first_k_dense_replace": 3, + "num_hidden_layers": 92, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "num_nextn_predict_layers": 1, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.54.0", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552, + "quantization_config": { + "quant_method": "gptq_marlin", + "bits": 4, + "group_size": 128, + "sym": true, + "desc_act": false, + "dynamic": { + "-:model.embed_tokens.weight": {}, + "-:.*shared_experts": {}, + "-:.*shared_head": {}, + "-:lm_head.weight": {}, + "+:model[.]layers[.]([0-4]|9[0-2])[.].*": { + "bits": 8 + } + } + } +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..f9291c34499303a5103dea21c45e605bb20981bb --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d49113f3e19072368c98e53180331c77c07c8a6 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "transformers_version": "4.54.0" +} diff --git a/model-00001-of-00042.safetensors b/model-00001-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19daf20f8c9e31e194bcd8ea0bea1d475a642b25 --- /dev/null +++ b/model-00001-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f46be18c5c61ad77e75b44481c02392f82d761ff7a734d85fa6bd274f841319 +size 4997791792 diff --git a/model-00002-of-00042.safetensors b/model-00002-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10b129d86543002f8c7d90f40d9376eeab99bf25 --- /dev/null +++ b/model-00002-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d0c23be7ba1c2c4a2f8e25e3ac1aca18faa729a0ac0231dc011340f2dab8862 +size 4995143368 diff --git a/model-00003-of-00042.safetensors b/model-00003-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..888d0e5bb3762d34ae858b5e9d98227c12efb732 --- /dev/null +++ b/model-00003-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119ee325fad2b030c9b18cfbdfde59e8fa520748e9a01eef54e6f13bd4a6ca62 +size 4998558160 diff --git a/model-00004-of-00042.safetensors b/model-00004-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d12f33bc29e718cbbeb8ee5d88f088ea8840cb5 --- /dev/null +++ b/model-00004-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f01b3af8cabb53ac62b9e03d9751fc7447620b7a21b88ac93c05c1a45ead73a +size 4997866008 diff --git a/model-00005-of-00042.safetensors b/model-00005-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85c1839177f03ead4821a07e88fe1944e72d20ba --- /dev/null +++ b/model-00005-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5715b92e0875862e66c6f6cfb4308e344933ace38939be051b0bca1a5fbd6d9e +size 4998724880 diff --git a/model-00006-of-00042.safetensors b/model-00006-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..754acc6a06bbec428c6adb8e6301510fdec0e822 --- /dev/null +++ b/model-00006-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd0166ddde1deda2605e9cfae0fbc6a6aa67ef5055adef790e782f82e616650 +size 4997885480 diff --git a/model-00007-of-00042.safetensors b/model-00007-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..372fdc0d23b00d7eba3c66bcbd130d53bf5ad90e --- /dev/null +++ b/model-00007-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d7b08652f20b58e62214cc90d68ba5e1db63e7bc2673413c34bc41271076eaa +size 4997870632 diff --git a/model-00008-of-00042.safetensors b/model-00008-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..699b6a19cab43b068302fc613c0f3b21bc23d4fc --- /dev/null +++ b/model-00008-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:652608a7e87e29bc971d87049b0271e9668dc9c97d2891c2fb886c507c2c3864 +size 4998727768 diff --git a/model-00009-of-00042.safetensors b/model-00009-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..83d91bddbd78c5fb48f33717c930c8238fef4065 --- /dev/null +++ b/model-00009-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f99aeb3c53dcdcb562a8b7dad870a4bb073b56e128a85f990d45472ebea7fa4 +size 4997870784 diff --git a/model-00010-of-00042.safetensors b/model-00010-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53735ace7822f0e33d14972b447c2253204b37ae --- /dev/null +++ b/model-00010-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6b93fe2d1f3bf1032d106987a3a7bf60f9a24cf03a6d3297326f5396e67dbf3 +size 4998727328 diff --git a/model-00011-of-00042.safetensors b/model-00011-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..517559958754861b2486b18efe98e96d2b0724ec --- /dev/null +++ b/model-00011-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c7c12475ba2bffebd3feae808826d71199472d52a415cbd041a923d8064b0c1 +size 4997885552 diff --git a/model-00012-of-00042.safetensors b/model-00012-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..efb5362a04b97262f1868ac2c47a837d66606503 --- /dev/null +++ b/model-00012-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67574ca8ddfef22e618bbc3f30a111b20cd1407b4a7e214e3542c880b42973a +size 4997870600 diff --git a/model-00013-of-00042.safetensors b/model-00013-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab7b427daed6619a4c82fbba1d1ca947a878bcbe --- /dev/null +++ b/model-00013-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d35d61b1d96d5f2e539e4db5d7d5a2c9577ebf45ee3018cb5cb64f8b922f98 +size 4998727688 diff --git a/model-00014-of-00042.safetensors b/model-00014-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..88bc755148133b7f8c12c51748649576d3c84f22 --- /dev/null +++ b/model-00014-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fe9ea1814714f05063d10f52608ba26f6c8eead6c5f70bcaa9561eecb9aab67 +size 4997870848 diff --git a/model-00015-of-00042.safetensors b/model-00015-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1c64ba7acf58d40d8b99b552e92ae8908904875 --- /dev/null +++ b/model-00015-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af3aa46d331a1f71b7a59d2f24404923dc09c1353ba2d62398ea6d27d115d07 +size 4998727256 diff --git a/model-00016-of-00042.safetensors b/model-00016-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe12ad946ed59b2dd46d23aec57df8982d905882 --- /dev/null +++ b/model-00016-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf76d7ccaad77b3a949b3da4e84df952474760d1883e46582c0c3862c053ff50 +size 4997885624 diff --git a/model-00017-of-00042.safetensors b/model-00017-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2589dd6a0be084bf887e92202c3020b8a373acdb --- /dev/null +++ b/model-00017-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f12cb86218ac0874e77ca060b98e3a1e26992e72da45eae7d14fd87e53a9b45 +size 4997870552 diff --git a/model-00018-of-00042.safetensors b/model-00018-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..40bca92ce29cb0c5cf236748f9d165ff2aa66fd2 --- /dev/null +++ b/model-00018-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eab1bae4f78987bfb1d3faa9d09c623743b828cd57671e2414e62e295a68e0b4 +size 4998727616 diff --git a/model-00019-of-00042.safetensors b/model-00019-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92be3ca09b93a0fbb9243c614945e2ea23f45aff --- /dev/null +++ b/model-00019-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c572c7086e1c2f8e846c63a7143123a965c5375580700ac09c0ace5ef67bfb +size 4997870928 diff --git a/model-00020-of-00042.safetensors b/model-00020-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b6c811a010a2e5dce62b4371b5cb49fa44e65bb4 --- /dev/null +++ b/model-00020-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b421afde37aa9f9d7deae828afedba5bca49690d0bb2738314c1e81c9d33735 +size 4998727200 diff --git a/model-00021-of-00042.safetensors b/model-00021-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8cc4b99ab0b1a84f310be5b89283b7455c4fab1 --- /dev/null +++ b/model-00021-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83d77013b648e243bccb682c6316c559994d687e21d2aa9267b14fa42bcc167c +size 4997885672 diff --git a/model-00022-of-00042.safetensors b/model-00022-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0fb14ab49571e481e97da99dee32febceda805d --- /dev/null +++ b/model-00022-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:391ee2914fbcd742e95e7b6638d9f1114f24573d15d58c12724249fae2e90dd6 +size 4997870560 diff --git a/model-00023-of-00042.safetensors b/model-00023-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a01c7db4ea2273164ca8729a7ef1c66d52dc29c --- /dev/null +++ b/model-00023-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5aaf6e316274fdbe49fb7e74d3030e923ef2ed3566f9b4c31faec7647881a0a +size 4998727544 diff --git a/model-00024-of-00042.safetensors b/model-00024-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff0682b6f22f505c8cb2fea30592135b2558029a --- /dev/null +++ b/model-00024-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87247632f93b563907e41d1c49cae6f5f93d4bffc7f4accafe3f1e357502a454 +size 4997870992 diff --git a/model-00025-of-00042.safetensors b/model-00025-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e488303e02856eaa5afdf57b407bdf9da6ad96e7 --- /dev/null +++ b/model-00025-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085fdc3105b20d70457ed941917f2be8891d2e4f74efe66a240320e546da18cc +size 4992074384 diff --git a/model-00026-of-00042.safetensors b/model-00026-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..09044100e8032d496462c137a7943b01a3bd584d --- /dev/null +++ b/model-00026-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e141471ee2844b34835a9762a5f430abbbfd55e17bb00f16506796690114c84 +size 5000431872 diff --git a/model-00027-of-00042.safetensors b/model-00027-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d66405c5457ae57eb33f90aa1ac587e2041c76a --- /dev/null +++ b/model-00027-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4782ffe566b700905c1f7308575794cc8a1ff3ac0a88cb18e60b9e34c8494d10 +size 4997870632 diff --git a/model-00028-of-00042.safetensors b/model-00028-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae71e657debb566123bc3a28d2f2b0fcd5ccccbf --- /dev/null +++ b/model-00028-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76437186c4d750f514dad4a658a946da715ccd39956c98c6b3a10a55a3f2cbd +size 4998727472 diff --git a/model-00029-of-00042.safetensors b/model-00029-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8aec0cad7796e006671bf066fa42f350d6692d0 --- /dev/null +++ b/model-00029-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6520a59490e95c2601fbd5189b999c2a177460927ce38c83dc31fb3a0870e924 +size 4997885424 diff --git a/model-00030-of-00042.safetensors b/model-00030-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b30046e6548e9685c8252569355f41923bf4e688 --- /dev/null +++ b/model-00030-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25cfb597302a5f0dbaa8f2e125d4e6fdc82102f6df9e8d1b11554dda48abd0b +size 4997870632 diff --git a/model-00031-of-00042.safetensors b/model-00031-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..929931b216c24e14d77d005fbc2f117218ce713a --- /dev/null +++ b/model-00031-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd7f8b1d038061d82c622f1312957e0fc71527a5866b155a3d337f6e23f1e2e +size 4998727920 diff --git a/model-00032-of-00042.safetensors b/model-00032-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ca0e650fae21161d4e8aea8ca5b26509b386e14 --- /dev/null +++ b/model-00032-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d05c7451e1ee61e6743f8fec34616f0f264087a61accb64d2bb2beef87af2db4 +size 4997870704 diff --git a/model-00033-of-00042.safetensors b/model-00033-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..680513b5ee17523e0911933d279cceaad2d46ab4 --- /dev/null +++ b/model-00033-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e84066f314fb27dec57a9c926ee44b38efa5e356689bbf72bac0049a476b5c +size 4998727400 diff --git a/model-00034-of-00042.safetensors b/model-00034-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3207473c1a51524e79cc2a5ac7210b4d3bfeb0b1 --- /dev/null +++ b/model-00034-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8df659065fb44433c1c9f3c7072f49f1dcb208c1acb3c2dcca5d9c0884c7788 +size 4997885480 diff --git a/model-00035-of-00042.safetensors b/model-00035-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d6ce01316303c4abb055e0a219536ad72e78e92 --- /dev/null +++ b/model-00035-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70521cac48074544b02ecacb87ebda92ffd0561e313a7caac92dbce7867aa01 +size 4997870632 diff --git a/model-00036-of-00042.safetensors b/model-00036-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc4e4cf7d7a127a4ea836d7d636064f808e1e535 --- /dev/null +++ b/model-00036-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd8902455f4b079b11938d21bfd8c18cc184bb1e5575f92df030f7ab5ec9520 +size 4998727768 diff --git a/model-00037-of-00042.safetensors b/model-00037-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cdf3ebe24f56c697ed9542b3532e715a726985a5 --- /dev/null +++ b/model-00037-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5e9f40e4d734b4709d9dd93ff15e2db656ceac53e5cc59ac55877fd1820641 +size 4997870784 diff --git a/model-00038-of-00042.safetensors b/model-00038-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4dd3de69e8e9e35e171e070d4733b2c0e037f8d3 --- /dev/null +++ b/model-00038-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cebed347d069631ce5954cb926aca7b088cdecbb38cd25fac4149a1d63c793d +size 5000057424 diff --git a/model-00039-of-00042.safetensors b/model-00039-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b65de9b8550e96a6958a24b5d94d96aba9405883 --- /dev/null +++ b/model-00039-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a806592646ceca0325e2ac917eb02769efaef3d2dee0ca1b66540aae3b6ac5e7 +size 3898292992 diff --git a/model-00040-of-00042.safetensors b/model-00040-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1183d5dade4ce9508f31b86b1ab4d6bf1d1ddd6 --- /dev/null +++ b/model-00040-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec535fba714a3a2a869a50a4311dfa699064e29567bc53ff4c2f9f9826970f0d +size 4995595616 diff --git a/model-00041-of-00042.safetensors b/model-00041-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd160a28a416ae567c6f7404aafc53c388d61d28 --- /dev/null +++ b/model-00041-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4d750640cbff926a5892cdcf1831747d3d9bcb0fc7208f73af0e2dea56e65c +size 4998632224 diff --git a/model-00042-of-00042.safetensors b/model-00042-of-00042.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..998818f6f741f8f8127b3914894c2df3c1e6afbb --- /dev/null +++ b/model-00042-of-00042.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a3be345ac099740315f5e48e4e0c5914fd7e9c319a08c948bd33a65570454c +size 1333687200 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8ef744d2f29a3d1a6c1172ac4302e16e7c821b36 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49dbd0a1da7cc76fa1f14902f4cec3fb5b658d056da59b652a4345e3e27fdfaf +size 15871572 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..43a71efad1ab3f7e4d66d1e48e7cc44f68f21f3a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd +size 19970699 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..053f12c9b03d5acbcc921042ea0c87a6baa5d3f7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,325 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizer" +}