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

Open

opened

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

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