[GH-ISSUE #45] 关于模型指标有一些疑问 #28

Open
opened 2026-10-26 21:01:50 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @MangoFF on GitHub (Mar 26, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/45

为什么Deepseek-Math-7B-rl 已经到了88.2%,但是DeepSeek-LLM-67B Chat只有84%?67B的综合模型,在数学能力上比7B的Math专有模型要差。

Originally created by @MangoFF on GitHub (Mar 26, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/45 为什么Deepseek-Math-7B-rl 已经到了88.2%,但是DeepSeek-LLM-67B Chat只有84%?67B的综合模型,在数学能力上比7B的Math专有模型要差。
Author
Owner

@MangoFF commented on GitHub (Mar 26, 2024):

提问仅代表个人观点

<!-- gh-comment-id:2019288527 --> @MangoFF commented on GitHub (Mar 26, 2024): 提问仅代表个人观点
Sign in to join this conversation.
No labels
bug
pull-request
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-LLM#28
No description provided.