对于系统上的一些参数，文档上描述不是很全面，麻烦解答一下 #2676
Milestone
Comments
|
应该可以不用填。如果你是用的已有的 model family，应该会继承。 |
|
蹲蹲答案 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
System Info / 系統信息
3090显卡*2
Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？
Version info / 版本信息
v1.0.1
The command used to start Xinference / 用以启动 xinference 的命令
系统启动
Reproduction / 复现过程
我在使用xinference上传自定义模型（qwen2.5-32b-gptq-int8）的时候，stop_token_ids、stop这2个停止参数不知道应该如何设置，系统上提醒了，从generation_config.json与tokenizer_config.json上面找。但是我这两个文件有没有相同的字段名称，对于我们不是很专业的人来说就不知道如何设置了。我的文件如下。麻烦解答，感谢~！！！！
tokenizer_config.json
{ "add_bos_token": false, "add_prefix_space": false, "added_tokens_decoder": { "151643": { "content": "<|endoftext|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151644": { "content": "<|im_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151645": { "content": "<|im_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151646": { "content": "<|object_ref_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151647": { "content": "<|object_ref_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151648": { "content": "<|box_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151649": { "content": "<|box_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151650": { "content": "<|quad_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151651": { "content": "<|quad_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151652": { "content": "<|vision_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151653": { "content": "<|vision_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151654": { "content": "<|vision_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151655": { "content": "<|image_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151656": { "content": "<|video_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151657": { "content": "<tool_call>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151658": { "content": "</tool_call>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151659": { "content": "<|fim_prefix|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151660": { "content": "<|fim_middle|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151661": { "content": "<|fim_suffix|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151662": { "content": "<|fim_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151663": { "content": "<|repo_name|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151664": { "content": "<|file_sep|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false } }, "additional_special_tokens": [ "<|im_start|>", "<|im_end|>", "<|object_ref_start|>", "<|object_ref_end|>", "<|box_start|>", "<|box_end|>", "<|quad_start|>", "<|quad_end|>", "<|vision_start|>", "<|vision_end|>", "<|vision_pad|>", "<|image_pad|>", "<|video_pad|>" ], "bos_token": null, "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", "clean_up_tokenization_spaces": false, "eos_token": "<|im_end|>", "errors": "replace", "model_max_length": 131072, "pad_token": "<|endoftext|>", "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null }generation_config.json
{ "bos_token_id": 151643, "do_sample": true, "eos_token_id": [ 151645, 151643 ], "pad_token_id": 151643, "repetition_penalty": 1.05, "temperature": 0.7, "top_k": 20, "top_p": 0.8, "transformers_version": "4.39.3" }Expected behavior / 期待表现
我在使用xinference上传自定义模型（qwen2.5-32b-gptq-int8）的时候，stop_token_ids、stop这2个停止参数不知道应该如何设置，系统上提醒了，从generation_config.json与tokenizer_config.json上面找。但是我这两个文件有没有相同的字段名称，对于我们不是很专业的人来说就不知道如何设置了。我的文件如下。麻烦解答，感谢~！！！！
tokenizer_config.json
{ "add_bos_token": false, "add_prefix_space": false, "added_tokens_decoder": { "151643": { "content": "<|endoftext|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151644": { "content": "<|im_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151645": { "content": "<|im_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151646": { "content": "<|object_ref_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151647": { "content": "<|object_ref_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151648": { "content": "<|box_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151649": { "content": "<|box_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151650": { "content": "<|quad_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151651": { "content": "<|quad_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151652": { "content": "<|vision_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151653": { "content": "<|vision_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151654": { "content": "<|vision_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151655": { "content": "<|image_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151656": { "content": "<|video_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151657": { "content": "<tool_call>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151658": { "content": "</tool_call>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151659": { "content": "<|fim_prefix|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151660": { "content": "<|fim_middle|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151661": { "content": "<|fim_suffix|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151662": { "content": "<|fim_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151663": { "content": "<|repo_name|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151664": { "content": "<|file_sep|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false } }, "additional_special_tokens": [ "<|im_start|>", "<|im_end|>", "<|object_ref_start|>", "<|object_ref_end|>", "<|box_start|>", "<|box_end|>", "<|quad_start|>", "<|quad_end|>", "<|vision_start|>", "<|vision_end|>", "<|vision_pad|>", "<|image_pad|>", "<|video_pad|>" ], "bos_token": null, "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", "clean_up_tokenization_spaces": false, "eos_token": "<|im_end|>", "errors": "replace", "model_max_length": 131072, "pad_token": "<|endoftext|>", "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null }generation_config.json
{ "bos_token_id": 151643, "do_sample": true, "eos_token_id": [ 151645, 151643 ], "pad_token_id": 151643, "repetition_penalty": 1.05, "temperature": 0.7, "top_k": 20, "top_p": 0.8, "transformers_version": "4.39.3" }麻烦解答，感谢~！！！！么么哒
The text was updated successfully, but these errors were encountered: