[trainer] Add LD-DPO objective (#8362)

src/llamafactory/hparams/finetuning_args.py

@@ -202,6 +202,10 @@ class RLHFArguments:
         default="lora",
         metadata={"help": "The type of the reward model in PPO training. Lora model only supports lora training."},
     )
+    ld_alpha: Optional[float] = field(
+        default=None,
+        metadata={"help": "α parameter from the LD-DPO paper, which controls the weighting of the verbose token log-probabilities in responses"},
+    )
 
 
 @dataclass