Add GRPO and Support RLVR for PPO (#6186)

* add grpo, support rlvr

* add grpo, support rlvr

* tested deepseek r1 pipeline

* add ci

* verify grpo r1

* verify grpo r1

* update readme, remove unused code

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* remove path

* clean code

* fix circular import

* fix ci OOM

* fix ci OOM

* skip kto tp, fix qwen generation

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

applications/ColossalChat/coati/models/__init__.py

@@ -4,12 +4,14 @@ from .generation import generate, generate_streaming, prepare_inputs_fn, update_
 from .lora import LoraConfig, convert_to_lora_module, lora_manager
 from .loss import DpoLoss, KTOLoss, LogExpLoss, LogSigLoss, PolicyLoss, ValueLoss
 from .reward_model import RewardModel
+from .rlvr_reward_model import RLVRRewardModel
 from .utils import disable_dropout
 
 __all__ = [
     "BaseModel",
     "Critic",
     "RewardModel",
+    "RLVRRewardModel",
     "PolicyLoss",
     "ValueLoss",
     "LogSigLoss",