feat(project_structure): 重构项目目录并添加运行脚本
This commit is contained in:
@@ -0,0 +1,9 @@
|
||||
from datasets import load_dataset
|
||||
from utils import process_dataset
|
||||
|
||||
if __name__ == "__main__":
|
||||
dataset = load_dataset("HuggingFaceFW/fineweb", "sample-10BT")
|
||||
process_dataset(
|
||||
dataset_dict=dataset,
|
||||
output_subdir="english-fineweb",
|
||||
)
|
||||
Reference in New Issue
Block a user