[GH-ISSUE #404] DeepSeek-R1 微调、蒸馏过后一直回复不停止 #317

Closed
opened 2026-10-26 21:19:19 +00:00 by bsakaguchi · 2 comments
Owner

Originally created by @shenriver on GitHub (Feb 14, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/404

DeepSeek-R1 微调、蒸馏过后一直回复不停止。建了个群大家一起交流

Image

Originally created by @shenriver on GitHub (Feb 14, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/404 DeepSeek-R1 微调、蒸馏过后一直回复不停止。建了个群大家一起交流 ![Image](https://github.com/user-attachments/assets/bb1570d2-013f-4f52-a9c6-3a3507d2488a)
Author
Owner

@kkllqw commented on GitHub (Feb 15, 2025):

不是很清楚,但是如果在微调时,你才用了不适配当前模型的模板构建微调数据,模型会出现你这样的问题。

<!-- gh-comment-id:2660772454 --> @kkllqw commented on GitHub (Feb 15, 2025): 不是很清楚,但是如果在微调时,你才用了不适配当前模型的模板构建微调数据,模型会出现你这样的问题。
Author
Owner

@mowentian commented on GitHub (Feb 19, 2025):

温馨提示:除 DeepSeek 官方用户交流微信群外,我们从未在其他平台设立任何群组

<!-- gh-comment-id:2668193976 --> @mowentian commented on GitHub (Feb 19, 2025): 温馨提示:除 DeepSeek 官方用户交流微信群外,我们从未在其他平台设立任何群组
Sign in to join this conversation.
No milestone
No project
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-R1#317
No description provided.