support DPO training (2305.18290)

Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f

src/llmtuner/hparams/general_args.py

@@ -4,10 +4,10 @@ from dataclasses import dataclass, field
 
 @dataclass
 class GeneralArguments:
-    """
+    r"""
     Arguments pertaining to which stage we are going to perform.
     """
-    stage: Optional[Literal["pt", "sft", "rm", "ppo"]] = field(
+    stage: Optional[Literal["pt", "sft", "rm", "ppo", "dpo"]] = field(
         default="sft",
         metadata={"help": "Which stage will be performed in training."}
     )