Skip to content

如何使用deepseek distill过的model来RL finetune以及是否可以再A6000上运行 #55

Open

Description

@ft2023
No description provided.

Activity

  1. dhcode-cpp commented on Feb 24, 2025

    @dhcode-cpp
    Owner

    可以。

  2. ft2023 commented on Feb 25, 2025

    @ft2023
    Author

    有在A6000上复现成功的case么,能share下参数跟具体的setting么?我目前在A6000同参数的setting下得到下面的结果,不知道是啥原因

    Image
  3. dhcode-cpp commented on Feb 26, 2025

    @dhcode-cpp
    Owner

    有在A6000上复现成功的case.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions