[GH-ISSUE #77] Where can I find documentation about DeepSeek Finetune? #64

Closed
opened 2026-10-26 21:12:51 +00:00 by bsakaguchi · 3 comments
Owner

Originally created by @Rqcker on GitHub (Jan 25, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/77

Can I use Unlsoth or some tools to fine-tune this model?

Originally created by @Rqcker on GitHub (Jan 25, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/77 Can I use Unlsoth or some tools to fine-tune this model?
bsakaguchi 2026-10-26 21:12:51 +00:00
Author
Owner

@Charlesnorris509 commented on GitHub (Jan 26, 2025):

@Rqcker According to the README file mentions using Reinforcement Learning and Fine tuning for training purposes. It seems like you need to use https://github.com/sgl-project/sglang for the fine tuning process. I hope that my response was usefull to you

<!-- gh-comment-id:2614502012 --> @Charlesnorris509 commented on GitHub (Jan 26, 2025): @Rqcker According to the README file mentions using Reinforcement Learning and Fine tuning for training purposes. It seems like you need to use https://github.com/sgl-project/sglang for the fine tuning process. I hope that my response was usefull to you
Author
Owner

@github-actions[bot] commented on GitHub (Feb 26, 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!

<!-- gh-comment-id:2683623843 --> @github-actions[bot] commented on GitHub (Feb 26, 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!
Author
Owner

@github-actions[bot] commented on GitHub (Mar 14, 2025):

false

<!-- gh-comment-id:2722968556 --> @github-actions[bot] commented on GitHub (Mar 14, 2025): false
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#64
No description provided.