diff --git a/new_datasets/iterate_hf_dataset.py b/new_datasets/iterate_hf_dataset.py index d6bf1a734d6bc0b4d7c41674db50a3dbab41bb1b..a28023787070a5c9c7eb0d122f5d9b946bee1fa0 100644 --- a/new_datasets/iterate_hf_dataset.py +++ b/new_datasets/iterate_hf_dataset.py @@ -5,7 +5,8 @@ import datasets def iterate_dataset(dataset_path: str, dataset_name: Optional[str], cache_dir: str, split_name: str, items: int): - dataset_dict = datasets.load_dataset(dataset_path, dataset_name if len(dataset_name) > 0 else None, cache_dir) + dataset_dict = datasets.load_dataset(dataset_path, dataset_name if len(dataset_name) > 0 else None, + cache_dir=cache_dir) dataset = dataset_dict[split_name] for it in dataset[:items]: print(it)