fix dpo trainer

Former-commit-id: c160dd7cd86e296e32775ace2e4258a473449c41

src/llmtuner/model/parser.py

@@ -130,6 +130,9 @@ def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
     if finetuning_args.stage == "ppo" and model_args.shift_attn:
         raise ValueError("PPO training is incompatible with S^2-Attn.")
 
+    if finetuning_args.stage == "ppo" and finetuning_args.reward_model_type == "lora" and model_args.use_unsloth:
+        raise ValueError("Unsloth does not support lora reward model.")
+
     if training_args.max_steps == -1 and data_args.streaming:
         raise ValueError("Please specify `max_steps` in streaming mode.")