refactor(pretrain): 更新预训练数据集输出目录名称

2025-08-02 17:29:21 +08:00
parent 931403a713
commit 241e24c400
7 changed files with 8 additions and 8 deletions
@@ -36,6 +36,6 @@ if __name__ == "__main__":
    
    process_dataset(
        dataset_dict=DatasetDict({"train": combined_dataset}),
-        output_subdir="chinese-instruct",
+        output_subdir="chinese-instruct-sft",
        process_func=process_func,
    )