refactor(dataset): 更新数据集加载路径和处理代码
This commit is contained in:
@@ -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(
|
||||
|
||||
Reference in New Issue
Block a user