Skip to content

能否直接提供强化学习完成的模型权重? #19

Description

@shiqiuchangatp

作者您好!这篇文章将GRPO算法应用到了知识图谱+RAG领域非常的令人瞩目,但是如果我们复现的时候手边没有大现存的A100(80G)显卡,比较难以复现代码段中的强化学习部分,同时又很想直接推理结果。请问您是否方便直接提供强化学习完成之后的模型权重?

Activity

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

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions