feat(project_structure): 重构项目目录并添加运行脚本

This commit is contained in:
2025-08-01 17:41:49 +08:00
parent c4ce882d56
commit 2d1c4e9d6c
12 changed files with 75 additions and 2 deletions
+9
View File
@@ -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",
)