GRPO as part of HF TRL?

[JumpingRain]

Feature request

Qwen2.5-Math and Qwen2.5-Code are two state-of-the-art models that have recently integrated GRPO (Group Relative Policy Optimization)

Motivation

https://qwenlm.github.io/blog/qwen2.5-math/ https://arxiv.org/pdf/2402.03300

Your contribution

This is a request-only post, so I don't contribute anything to it.

[lewtun]

Hello @JumpingRain there is an open PR for this in #1954 that is currently under development

[fzyzcjy]

+1 It would be great to have this, looking forward to it!