support DPO training (2305.18290)

Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
2023-08-11 03:02:53 +08:00
parent 72dfd74005
commit ca719a8697
33 changed files with 513 additions and 192 deletions
--- a/src/llmtuner/hparams/data_args.py
+++ b/src/llmtuner/hparams/data_args.py
@@ -24,7 +24,7 @@ class DatasetAttr:

@dataclass
 class DataArguments:
-    """
+    r"""
    Arguments pertaining to what data we are going to input our model for training and evaluation.
    """
    template: str = field(