Skip to content

后续可以考虑出一个和verl或者OpenRLHF兼容的版本吗,用于做RL的reward model #484

@Shawcsy

Description

@Shawcsy

如题,现在的多模态rewardmodel太少了,好不容易找到一个还很难和rl的框架兼容

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions