Upload train_grpo.py with huggingface_hub

train_grpo.py

@@ -158,7 +158,7 @@ class QMDRewardFunction:
         self.embedder = SentenceTransformer('all-MiniLM-L6-v2')
         print("Embedding model loaded.")
 
-    def __call__(self, completions: list[str], prompts: list[str] = None) -> list[float]:
+    def __call__(self, completions: list[str], prompts: list[str] = None, **kwargs) -> list[float]:
         """Compute rewards for a batch of completions."""
         rewards = []