[Feature] VLMs support for GRPO (#4265)
* Updated rl and rl_replacements * Revert "Updated rl and rl_replacements" This reverts commit 077fd5996daa73c9c58c9f213657f33f47f5d73b. --------- Co-authored-by: Sinoué GAD <85933501+GAD-cell@users.noreply.github.com>
This commit is contained in:
parent
74c1497f2f
commit
1ca441a3f3