refactor(utils): 重构数据处理脚本

This commit is contained in:
2025-07-15 13:10:38 +08:00
parent e6f5b26a75
commit e77fb56c45
5 changed files with 20 additions and 21 deletions
+3 -1
View File
@@ -1,8 +1,10 @@
from datasets import load_dataset
from utils import process_dataset
if __name__ == "__main__":
dataset = load_dataset("Blaze7451/enwiki_structured_content")
process_dataset(
dataset_name="Blaze7451/enwiki_structured_content",
dataset_dict=dataset,
output_subdir="english-wiki",
max_chunk_size=5,
)