diff --git a/configs/model_config.py.example b/configs/model_config.py.example
index 66ef4e8..87a3c89 100644
--- a/configs/model_config.py.example
+++ b/configs/model_config.py.example
@@ -179,6 +179,8 @@ MODEL_PATH = {
 
         "Qwen-14B": "Qwen/Qwen-14B",
         "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
+        # 在新版的transformers下需要手动修改模型的config.json文件，在quantization_config字典中
+        # 增加`disable_exllama:true` 字段才能启动qwen的量化模型
         "Qwen-14B-Chat-Int8": "Qwen/Qwen-14B-Chat-Int8",
         "Qwen-14B-Chat-Int4": "Qwen/Qwen-14B-Chat-Int4",