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 #317] 为什么我用transformer使用模型会有奇怪回复 #245

New issue
Closed
opened 2026-10-26 21:17:47 +00:00 by bsakaguchi · 6 comments
bsakaguchi commented 2026-10-26 21:17:47 +00:00
Owner
Copy link

Originally created by @panrc on GitHub (Feb 7, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/317

imageimage

Originally created by @panrc on GitHub (Feb 7, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/317 ![image](https://github.com/user-attachments/assets/231685fd-b24e-40bb-a795-ac54258239c6)![image](https://github.com/user-attachments/assets/b90b66ae-b36b-44ba-96a1-c5cdb23206a2)
bsakaguchi 2026-10-26 21:17:47 +00:00
bsakaguchi commented 2026-10-26 21:17:49 +00:00
Author
Owner
Copy link

@panrc commented on GitHub (Feb 7, 2025):

权重，配置都是用hf上的

<!-- gh-comment-id:2643583384 --> @panrc commented on GitHub (Feb 7, 2025): 权重，配置都是用hf上的
bsakaguchi commented 2026-10-26 21:17:49 +00:00
Author
Owner
Copy link

@FrankMinions commented on GitHub (Feb 8, 2025):

权重，配置都是用hf上的

你应该是没添加对话模板

<!-- gh-comment-id:2644421510 --> @FrankMinions commented on GitHub (Feb 8, 2025): > 权重，配置都是用hf上的 你应该是没添加对话模板
bsakaguchi commented 2026-10-26 21:17:50 +00:00
Author
Owner
Copy link

@deepsicker commented on GitHub (Feb 8, 2025):

你现在每次会话，模型并没有关注到之前的历史会话内容。也就是注意力不够。会话功能要借助langchain 以及支持会话功能的模型比如deepseek-chat。 才能实现会话功能。下面是个demo
https://www.yuque.com/unreal/gpynrn/ex97qx9y9wy5mrcy

<!-- gh-comment-id:2644496688 --> @deepsicker commented on GitHub (Feb 8, 2025): 你现在每次会话，模型并没有关注到之前的历史会话内容。也就是注意力不够。会话功能要借助langchain 以及支持会话功能的模型比如deepseek-chat。 才能实现会话功能。下面是个demo https://www.yuque.com/unreal/gpynrn/ex97qx9y9wy5mrcy
bsakaguchi commented 2026-10-26 21:17:50 +00:00
Author
Owner
Copy link

@panrc commented on GitHub (Feb 8, 2025):

权重，配置都是用hf上的

你应该是没添加对话模板

应该是的

<!-- gh-comment-id:2644498401 --> @panrc commented on GitHub (Feb 8, 2025): > > 权重，配置都是用hf上的 > > 你应该是没添加对话模板 应该是的
bsakaguchi commented 2026-10-26 21:17:50 +00:00
Author
Owner
Copy link

@github-actions[bot] commented on GitHub (Mar 28, 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:2759861241 --> @github-actions[bot] commented on GitHub (Mar 28, 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 21:17:50 +00:00
Author
Owner
Copy link

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

false

<!-- gh-comment-id:2848300457 --> @github-actions[bot] commented on GitHub (May 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#245
No description provided.