diff --git a/config.py b/config.py
index 44e9f07..a511724 100644
--- a/config.py
+++ b/config.py
@@ -101,6 +101,8 @@ MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
 
 
 # 选择本地模型变体（只有当AVAIL_LLM_MODELS包含了对应本地模型时，才会起作用）
+# 如果你选择Qwen系列的模型，那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
+# 也可以是具体的模型路径
 QWEN_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
 
 
diff --git a/request_llms/bridge_qwen.py b/request_llms/bridge_qwen.py
index 1bd846b..940c41d 100644
--- a/request_llms/bridge_qwen.py
+++ b/request_llms/bridge_qwen.py
@@ -22,7 +22,7 @@ class GetQwenLMHandle(LocalLLMHandle):
         from transformers import AutoModelForCausalLM, AutoTokenizer
         from transformers.generation import GenerationConfig
         with ProxyNetworkActivate('Download_LLM'):
-            model_id = get_conf('QWEN_MODEL_SELECTION') #在这里更改路径，如果你已经下载好了的话，同时，别忘记tokenizer
+            model_id = get_conf('QWEN_MODEL_SELECTION')
             self._tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, resume_download=True)
             # use fp16
             model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True).eval()