refactor(utilsi): 优化项目结构

This commit is contained in:
2025-07-14 14:41:42 +08:00
parent 1c132826c0
commit 7e53d35099
3 changed files with 37 additions and 38 deletions
+1 -2
View File
@@ -2,8 +2,7 @@ from utils import process_dataset
if __name__ == "__main__":
process_dataset(
dataset_name="wikimedia/wikipedia",
dataset_name="Blaze7451/Wiki-zh-20250601",
output_subdir="chinese-wiki",
dataset_config="zh",
max_chunk_size=5,
)