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/reward_model.py

@@ -25,7 +25,9 @@ class RewardModel(BaseModel):
         self.value_head = nn.Linear(self.last_hidden_state_size, 1)
         self.value_head.weight.data.normal_(mean=0.0, std=1 / (self.last_hidden_state_size + 1))
 
-    def forward(self, input_ids: torch.LongTensor, attention_mask: Optional[torch.Tensor] = None) -> torch.Tensor:
+    def forward(
+        self, input_ids: torch.LongTensor, attention_mask: Optional[torch.Tensor] = None, **kwargs
+    ) -> torch.Tensor:
         outputs = self.model(input_ids, attention_mask=attention_mask)
 
         last_hidden_states = outputs["last_hidden_state"]