[GH-ISSUE #31] 偏好数据构造方法 #30

Closed
opened 2026-10-26 21:06:57 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @pandaupc on GitHub (May 15, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V2/issues/31

论文中提到:
We obtain code preference data based on compiler-feedback, and mathematical
preference data based on the ground-truth labels
可以详细讲一下是如何做的吗?

Originally created by @pandaupc on GitHub (May 15, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V2/issues/31 论文中提到: We obtain code preference data based on compiler-feedback, and mathematical preference data based on the ground-truth labels 可以详细讲一下是如何做的吗?
Author
Owner

@luofuli commented on GitHub (May 27, 2024):

技术报告外的信息暂无披露计划
@pandaupc

<!-- gh-comment-id:2133253140 --> @luofuli commented on GitHub (May 27, 2024): 技术报告外的信息暂无披露计划 @pandaupc
Sign in to join this conversation.
No labels
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-V2#30
No description provided.