Release v0.1.6

This commit is contained in:
hiyouga
2023-08-11 23:25:57 +08:00
parent 156710a995
commit a48cb0d474
18 changed files with 127 additions and 41 deletions

View File

@@ -93,11 +93,13 @@ def get_dataset(
dataset = dataset.rename_column(getattr(dataset_attr, column_name), column_name)
if dataset_attr.source_prefix: # add prefix
features = None
if data_args.streaming:
features = dataset.features
features["prefix"] = Value(dtype="string", id=None)
dataset = dataset.map(lambda _: {"prefix": dataset_attr.source_prefix}, features=features)
dataset = dataset.map(lambda _: {"prefix": dataset_attr.source_prefix}, features=features)
else:
prefix_data = [dataset_attr.source_prefix] * len(dataset)
dataset = dataset.add_column("prefix", prefix_data)
all_datasets.append(dataset)