mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2026-11-05 00:47:42 +00:00
[GH-ISSUE #350] Chat Template 更新后 vLLM reasoning-parser 无法正确处理 #273
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-R1#273
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @haowang02 on GitHub (Feb 10, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/350
注意到昨天 HuggingFace Hub 中 DeepSeek-R1 包括其蒸馏版本的 Chat Template (tokenizer_config.json 中) 有所更新,主要是在其末尾增加了
<think>\\n。我猜测这个更新是为了强制 DeepSeek-R1 从思考内容开始生成,从而避免其绕过思考。遗憾的是这个更新导致 vLLM 中的 reasoning-parser 不再按预期工作。
不知道 vLLM 中的 deepseek_r1 reasoning-parser 是哪边在维护,希望能尽快修复。
谢谢!
@deepsicker commented on GitHub (Feb 10, 2025):
不再按预期工作 是什么意思报错了? 还是?show your code,
我的代码这里没问题啊https://www.yuque.com/unreal/gpynrn/so9tml5v3dv9x6ra#UlZwT
@haowang02 commented on GitHub (Feb 10, 2025):
您好,这是我启动 vLLM 的命令:
成功启动后我用以下命令尝试对话:
以下是 vLLM 的返回结果:
可以看到 reasoning_content 字段为 null,而实际的思考内容包括
</think>标签都被包含在 content 字段中。我想这是预期的,因为在 HuggingFace Hub 中的 Chat Template 被更新前思考的内容能顺利被解析到 reasoning_content 字段中。
以下是我的系统信息:
@ariesfish commented on GitHub (Feb 10, 2025):
参考
https://github.com/deepseek-ai/DeepSeek-R1/issues/352#issuecomment-2647631744
可以解决
@newledge commented on GitHub (Feb 27, 2025):
你用openai的方式试过么?
@github-actions[bot] commented on GitHub (Apr 30, 2025):
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!