GRPO Trainer for VLM?

Research
1

Wonder HuggingFace has any plan to support GRPO Trainer or DPO Trainer for VLM?

It would be a huge contribution to the community.

2 Likes
3

sorry I just saw VLM part :slight_smile:

1 Like
4

Seems ongoing issue (request).

1 Like
5

any updates on this?

1 Like
6

Welcome first time posters @SabaPivot and @Cherran

1 Like
7

Someone wrote the code, but it doesn’t seem to have been committed yet.