fix #1658

Former-commit-id: 3126687c4820c34daa6a2e9e3bf9065ad59e92dc

src/llmtuner/train/rm/trainer.py

@@ -39,7 +39,8 @@ class PairwiseTrainer(Trainer):
         """
         # Compute rewards
         _, _, values = model(**inputs, output_hidden_states=True, return_dict=True)
-        if values.size(0) != inputs["input_ids"].size(0): # adapt to chatglm2
+
+        if getattr(model.config, "model_type", None) == "chatglm":
             values = torch.transpose(values, 0, 1)
 
         # Split the inputs and rewards into two parts, chosen and rejected