remove checksum and fix ui args

This commit is contained in:
hiyouga
2024-05-12 01:10:30 +08:00
parent d06d56661b
commit 58c522cd5c
8 changed files with 16 additions and 47 deletions

View File

@@ -26,21 +26,6 @@ class Role(str, Enum):
OBSERVATION = "observation"
def checksum(data_files: List[str], file_sha1: Optional[str] = None) -> None:
if file_sha1 is None:
logger.warning("Checksum failed: missing SHA-1 hash value in dataset_info.json.")
return
if len(data_files) != 1:
logger.warning("Checksum failed: too many files.")
return
with open(data_files[0], "rb") as f:
sha1 = hashlib.sha1(f.read()).hexdigest()
if sha1 != file_sha1:
logger.warning("Checksum failed: mismatched SHA-1 hash value at {}.".format(data_files[0]))
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)