support ORPO

Former-commit-id: f44a4c27e2461cdaa1b16865f597a31033c0e6d9

src/llmtuner/train/tuner.py

@@ -9,6 +9,7 @@ from ..extras.logging import get_logger
 from ..hparams import get_infer_args, get_train_args
 from ..model import load_model_and_tokenizer
 from .dpo import run_dpo
+from .orpo import run_orpo
 from .ppo import run_ppo
 from .pt import run_pt
 from .rm import run_rm
@@ -36,6 +37,8 @@ def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: Optional[List["Tra
         run_ppo(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
     elif finetuning_args.stage == "dpo":
         run_dpo(model_args, data_args, training_args, finetuning_args, callbacks)
+    elif finetuning_args.stage == "orpo":
+        run_orpo(model_args, data_args, training_args, finetuning_args, callbacks)
     else:
         raise ValueError("Unknown task.")