refactor(dataset): 重构数据处理脚本并支持自定义数据集

This commit is contained in:
2025-07-15 12:18:58 +08:00
parent 1c7e49a631
commit bea4f83842
5 changed files with 25 additions and 15 deletions
-1
View File
@@ -1,6 +1,5 @@
from utils import process_dataset
if __name__ == "__main__":
process_dataset(
dataset_name="HuggingFaceFW/fineweb",