deepseek-ai/DeepSeek-LLM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-LLM.git synced 2026-11-05 00:57:25 +00:00
Code Issues 62 Projects Packages Wiki Activity

[GH-ISSUE #37] 关于vllm使用的疑问 #24

New issue
Closed
opened 2026-10-26 21:01:47 +00:00 by bsakaguchi · 1 comment
bsakaguchi commented 2026-10-26 21:01:47 +00:00
Owner
Copy link

Originally created by @xuyifan-0731 on GitHub (Feb 1, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/37

你好！在使用官方提供的vllm代码的时候，我有一个问题：
prompts = [tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) for messages in messages_list]
这一步操作之后，实际的生成结果是一个字符串序列。但是诸如<｜begin▁of▁sentence｜>等其实应该是作为special token拼接的。请问这样使用是否是正确的？

Originally created by @xuyifan-0731 on GitHub (Feb 1, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/37 你好！在使用官方提供的vllm代码的时候，我有一个问题： prompts = [tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) for messages in messages_list] 这一步操作之后，实际的生成结果是一个字符串序列。但是诸如<｜begin▁of▁sentence｜>等其实应该是作为special token拼接的。请问这样使用是否是正确的？
bsakaguchi 2026-10-26 21:01:47 +00:00
  • closed this issue
  • added the
    bug
         label
bsakaguchi commented 2026-10-26 21:01:48 +00:00
Author
Owner
Copy link

@luofuli commented on GitHub (Feb 4, 2024):

你好！在使用官方提供的vllm代码的时候，我有一个问题： prompts = [tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) for messages in messages_list] 这一步操作之后，实际的生成结果是一个字符串序列。但是诸如<｜begin▁of▁sentence｜>等其实应该是作为special token拼接的。请问这样使用是否是正确的？

Thanks for pointing out this bug. We've already fixed it.
https://github.com/deepseek-ai/DeepSeek-LLM/pull/39/commits/ebec08a377ab5a770472d8353ecd75137e9f1f36

<!-- gh-comment-id:1925798778 --> @luofuli commented on GitHub (Feb 4, 2024): > 你好！在使用官方提供的vllm代码的时候，我有一个问题： prompts = [tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) for messages in messages_list] 这一步操作之后，实际的生成结果是一个字符串序列。但是诸如<｜begin▁of▁sentence｜>等其实应该是作为special token拼接的。请问这样使用是否是正确的？ Thanks for pointing out this bug. We've already fixed it. https://github.com/deepseek-ai/DeepSeek-LLM/pull/39/commits/ebec08a377ab5a770472d8353ecd75137e9f1f36
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
bug

   
pull-request
Mirrored from GitHub Pull Request

No labels
bug
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-LLM#24
No description provided.