refactor(dataset): 重构数据集处理流程并添加新功能

This commit is contained in:
2025-07-16 09:56:31 +08:00
parent 6edc31ce2e
commit b69ba2c5ff
8 changed files with 30 additions and 13 deletions
+2 -2
View File
@@ -1,9 +1,9 @@
from datasets import load_dataset
from utils import process_dataset
from utils import pre_tarin_process
if __name__ == "__main__":
dataset = load_dataset("shjwudp/chinese-c4")
process_dataset(
pre_tarin_process(
dataset_dict=dataset,
output_subdir="chinese-c4"
)