feat(chinese-wiki., english-wiki.): 添加 max_chunk_size 参数

This commit is contained in:
2025-07-14 13:35:06 +08:00
parent 820ddf3fc8
commit 1c132826c0
2 changed files with 4 additions and 2 deletions
+2 -1
View File
@@ -4,5 +4,6 @@ if __name__ == "__main__":
process_dataset(
dataset_name="wikimedia/wikipedia",
output_subdir="chinese-wiki",
dataset_config="zh"
dataset_config="zh",
max_chunk_size=5,
)
+2 -1
View File
@@ -3,5 +3,6 @@ from utils import process_dataset
if __name__ == "__main__":
process_dataset(
dataset_name="Blaze7451/enwiki_structured_content",
output_subdir="english-wiki"
output_subdir="english-wiki",
max_chunk_size=5,
)