deepseek-ai/DeepSeek-R1
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-R1.git synced 2026-11-05 00:47:42 +00:00
Code Issues 45 Projects Packages Wiki Activity

[GH-ISSUE #653] deekseek-r1复现问题求助-有尝试基于deepseek-v3来复现R1的么 #531

New issue
Closed
opened 2026-10-26 21:22:42 +00:00 by bsakaguchi · 3 comments
bsakaguchi commented 2026-10-26 21:22:42 +00:00
Owner
Copy link

Originally created by @jerry123888 on GitHub (May 7, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/653

求问各位大佬，目前业务侧在尝试将私域内积累的知识使用R1复现的思路，基于一个基座模型，通过SFT+GRPO来训练出一个自己领域内的R1。 但是找了一些开源的复现R1的项目发现，几乎基座模型他们选用的都是qwen2.5-7B的，目前未碰到有基于deepseek-V3来尝试复现R1的，请问大佬们知道有哪个开源项目是基于deepseek-v3来复现r1的么？

Originally created by @jerry123888 on GitHub (May 7, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/653 求问各位大佬，目前业务侧在尝试将私域内积累的知识使用R1复现的思路，基于一个基座模型，通过SFT+GRPO来训练出一个自己领域内的R1。 但是找了一些开源的复现R1的项目发现，几乎基座模型他们选用的都是qwen2.5-7B的，目前未碰到有基于deepseek-V3来尝试复现R1的，请问大佬们知道有哪个开源项目是基于deepseek-v3来复现r1的么？
bsakaguchi 2026-10-26 21:22:42 +00:00
bsakaguchi commented 2026-10-26 21:22:44 +00:00
Author
Owner
Copy link

@Kenwwww commented on GitHub (May 19, 2025):

求问各位大佬，目前业务侧在尝试将私域内积累的知识使用R1复现的思路，基于一个基座模型，通过SFT+GRPO来训练出一个自己领域内的R1。 但是找了一些开源的复现R1的项目发现，几乎基座模型他们选用的都是qwen2.5-7B的，目前未碰到有基于deepseek-V3来尝试复现R1的，请问大佬们知道有哪个开源项目是基于deepseek-v3来复现r1的么？

佬，有结果了吗？我这边只尝试过直接在思维链版本上进行cpt和蒸馏微调，大致能看到私域知识进去了，但同样不清楚从头走一遍训练流程是否能提高现在的上限。

<!-- gh-comment-id:2889831859 --> @Kenwwww commented on GitHub (May 19, 2025): > 求问各位大佬，目前业务侧在尝试将私域内积累的知识使用R1复现的思路，基于一个基座模型，通过SFT+GRPO来训练出一个自己领域内的R1。 但是找了一些开源的复现R1的项目发现，几乎基座模型他们选用的都是qwen2.5-7B的，目前未碰到有基于deepseek-V3来尝试复现R1的，请问大佬们知道有哪个开源项目是基于deepseek-v3来复现r1的么？ 佬，有结果了吗？我这边只尝试过直接在思维链版本上进行cpt和蒸馏微调，大致能看到私域知识进去了，但同样不清楚从头走一遍训练流程是否能提高现在的上限。
bsakaguchi commented 2026-10-26 21:22:44 +00:00
Author
Owner
Copy link

@github-actions[bot] commented on GitHub (Jun 19, 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:2986091663 --> @github-actions[bot] commented on GitHub (Jun 19, 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!
bsakaguchi commented 2026-10-26 21:22:44 +00:00
Author
Owner
Copy link

@github-actions[bot] commented on GitHub (Jul 3, 2025):

false

<!-- gh-comment-id:3029765370 --> @github-actions[bot] commented on GitHub (Jul 3, 2025): false
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
v1.0.0
Labels
Clear labels   
bug

   
closed-as-stale

   
closed-as-stale

   
enhancement

   
pull-request
Mirrored from GitHub Pull Request

  
stale

   
stale
No labels
bug
closed-as-stale
closed-as-stale
enhancement
pull-request
stale
stale
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-R1#531
No description provided.