refactor(pretrain): 更新预训练数据集输出目录名称

This commit is contained in:
2025-08-02 17:29:21 +08:00
parent 931403a713
commit 241e24c400
7 changed files with 8 additions and 8 deletions
+1 -1
View File
@@ -5,6 +5,6 @@ if __name__ == "__main__":
dataset = load_dataset("Blaze7451/enwiki_structured_content")
process_dataset(
dataset_dict=dataset,
output_subdir="english-wiki",
output_subdir="english-wiki-pretrain",
max_chunk_size=5,
)