[GH-ISSUE #449] 能蒸馏个QWEN 72B的吗? #358

Closed
opened 2026-10-26 21:19:57 +00:00 by bsakaguchi · 2 comments
Owner

Originally created by @dkasa on GitHub (Feb 18, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/449

能蒸馏个QWEN 72B的吗?由于一些原因,国内还是不想用llama。感谢~~

Originally created by @dkasa on GitHub (Feb 18, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/449 能蒸馏个QWEN 72B的吗?由于一些原因,国内还是不想用llama。感谢~~
Author
Owner

@a984120978 commented on GitHub (Feb 19, 2025):

72B效果不比32B强多少,所以没必要

<!-- gh-comment-id:2667314155 --> @a984120978 commented on GitHub (Feb 19, 2025): 72B效果不比32B强多少,所以没必要
Author
Owner

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

建议移步相关社区以寻求支持~

<!-- gh-comment-id:2668190585 --> @mowentian commented on GitHub (Feb 19, 2025): 建议移步相关社区以寻求支持~
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#358
No description provided.