feat(project_structure): 重构项目目录并添加运行脚本

This commit is contained in:
2025-08-01 17:41:49 +08:00
parent c4ce882d56
commit 2d1c4e9d6c
12 changed files with 75 additions and 2 deletions
+18
View File
@@ -0,0 +1,18 @@
from datasets import load_dataset
from utils import process_dataset
if __name__ == "__main__":
max_chunk_num = 10
chunk_size = 1000000
dataset = load_dataset(
"opencsg/chinese-cosmopedia",
data_files={"train": [f"data/0000{i}.parquet" for i in range(5)]}
)
process_dataset(
dataset_dict=dataset,
output_subdir="chinese-wiki",
max_chunk_num=max_chunk_num,
chunk_size=chunk_size,
)