release v0.6.2

This commit is contained in:
hiyouga
2024-04-11 20:08:51 +08:00
parent 51d0a1a19e
commit 9d4c949461
10 changed files with 37 additions and 26 deletions

View File

@@ -53,22 +53,35 @@ class DatasetAttr:
def get_dataset_list(data_args: "DataArguments") -> List["DatasetAttr"]:
dataset_names = [ds.strip() for ds in data_args.dataset.split(",")] if data_args.dataset is not None else []
try:
with open(os.path.join(data_args.dataset_dir, DATA_CONFIG), "r") as f:
dataset_info = json.load(f)
except Exception as err:
if data_args.dataset is not None:
raise ValueError(
"Cannot open {} due to {}.".format(os.path.join(data_args.dataset_dir, DATA_CONFIG), str(err))
)
if data_args.dataset is not None:
dataset_names = [ds.strip() for ds in data_args.dataset.split(",")]
else:
dataset_names = []
if data_args.dataset_dir == "ONLINE":
dataset_info = None
else:
try:
with open(os.path.join(data_args.dataset_dir, DATA_CONFIG), "r") as f:
dataset_info = json.load(f)
except Exception as err:
if len(dataset_names) != 0:
raise ValueError(
"Cannot open {} due to {}.".format(os.path.join(data_args.dataset_dir, DATA_CONFIG), str(err))
)
dataset_info = None
if data_args.interleave_probs is not None:
data_args.interleave_probs = [float(prob.strip()) for prob in data_args.interleave_probs.split(",")]
dataset_list: List[DatasetAttr] = []
for name in dataset_names:
if dataset_info is None:
load_from = "ms_hub" if use_modelscope() else "hf_hub"
dataset_attr = DatasetAttr(load_from, dataset_name=name)
dataset_list.append(dataset_attr)
continue
if name not in dataset_info:
raise ValueError("Undefined dataset {} in {}.".format(name, DATA_CONFIG))