From 5b93ca6c3975e69b42a4465f8d687e98cdb08631 Mon Sep 17 00:00:00 2001 From: BUAADreamer <1428195643@qq.com> Date: Sat, 10 Jun 2023 16:27:30 +0800 Subject: [PATCH] add code for reading from multi files in one directory Former-commit-id: 9b80cf08b9f0d4aee896b228fb76399e9a7c9d8b --- src/utils/common.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/src/utils/common.py b/src/utils/common.py index 5af5e8cc..71a7ebe7 100644 --- a/src/utils/common.py +++ b/src/utils/common.py @@ -358,12 +358,10 @@ def prepare_data( elif dataset_attr.load_from == "file": data_file = os.path.join(data_args.dataset_dir, dataset_attr.file_name) extension = dataset_attr.file_name.split(".")[-1] - if dataset_attr.file_sha1 is not None: checksum(data_file, dataset_attr.file_sha1) else: logger.warning("Checksum failed: missing SHA-1 hash value in dataset_info.json.") - print(extension) raw_datasets = load_dataset( extension if extension in ["csv", "json"] else "text", data_files=data_file,