refactor(pretrain): 更新预训练数据集输出目录名称
This commit is contained in:
@@ -5,5 +5,5 @@ if __name__ == "__main__":
|
||||
dataset = load_dataset("HuggingFaceFW/fineweb", "sample-10BT")
|
||||
process_dataset(
|
||||
dataset_dict=dataset,
|
||||
output_subdir="english-fineweb",
|
||||
output_subdir="english-fineweb-pretrain",
|
||||
)
|
||||
Reference in New Issue
Block a user