refactor(dataset): 更新数据集加载路径和处理代码

This commit is contained in:
2025-07-15 14:06:18 +08:00
parent e77fb56c45
commit 6edc31ce2e
2 changed files with 1 additions and 2 deletions
+1 -1
View File
@@ -7,7 +7,7 @@ if __name__ == "__main__":
dataset = load_dataset(
"opencsg/chinese-cosmopedia",
data_files=[f"0000{i}.parquet" for i in range(5)]
data_files={"train": [f"data/0000{i}.parquet" for i in range(5)]}
)
process_dataset(