refactor(pretrain): 更新预训练数据集输出目录名称

This commit is contained in:
2025-08-02 17:29:21 +08:00
parent 931403a713
commit 241e24c400
7 changed files with 8 additions and 8 deletions
+2 -2
View File
@@ -24,7 +24,7 @@ if __name__ == "__main__":
dataset = load_dataset("HuggingFaceTB/Magpie-Pro-300K-Filtered-H4")
process_dataset(
dataset_dict=dataset,
output_subdir="belle-sft",
output_subdir="Magpie-Pro-300K-sft",
process_func=process_func,
split_name="train-sft"
split_name="train_sft",
)