feat(dataset): 更新数据集处理和保存逻辑

2025-07-20 11:21:18 +08:00
parent 365086f102
commit fcb5c2bcc8
3 changed files with 17 additions and 2 deletions
@@ -32,6 +32,6 @@ if __name__ == "__main__":
    dataset = load_dataset("BelleGroup/train_3.5M_CN")
    process_dataset(
        dataset_dict=dataset,
-        output_subdir="belle_sft",
+        output_subdir="belle-sft",
        process_func=process_func,
    )