refactor(dataset): 重构数据集处理流程并添加新功能
This commit is contained in:
+2
-2
@@ -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("Blaze7451/enwiki_structured_content")
|
||||
process_dataset(
|
||||
pre_tarin_process(
|
||||
dataset_dict=dataset,
|
||||
output_subdir="english-wiki",
|
||||
max_chunk_size=5,
|
||||
|
||||
Reference in New Issue
Block a user