v0.5.0
fix style
[ColossalChat] Update RLHF V2 (#5286)
Add GRPO and Support RLVR for PPO (#6186)
[pre-commit.ci] auto fixes from pre-commit.com hooks
[ColossalChat] Add PP support (#6001)
[Coati] Train DPO using PP (#6054)
refactor tokenization