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.

3

sorry I just saw VLM part :slight_smile:

4

Seems ongoing issue (request).

5

any updates on this?

6

Welcome first time posters @SabaPivot and @Cherran

7

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