support ORPO

This commit is contained in:
hiyouga
2024-03-31 18:29:50 +08:00
parent 27776c3474
commit 17bf8a2c3a
22 changed files with 395 additions and 47 deletions

View File

@@ -44,7 +44,7 @@ def checksum(data_files: List[str], file_sha1: Optional[str] = None) -> None:
def infer_max_len(source_len: int, target_len: int, max_len: int, reserved_label_len: int) -> Tuple[int, int]:
max_target_len = int(max_len * (target_len / (source_len + target_len)))
max_target_len = max(max_target_len, reserved_label_len)
max_source_len = max_len - max_target_len
max_source_len = max_len - min(max_target_len, target_len)
return max_source_len, max_target_len