diff --git a/config.py b/config.py
index f170a2b..4284cb8 100644
--- a/config.py
+++ b/config.py
@@ -91,10 +91,10 @@ AVAIL_LLM_MODELS = ["gpt-3.5-turbo-1106","gpt-4-1106-preview","gpt-4-vision-prev
                     "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
                     "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
                     "gpt-4", "gpt-4-32k", "azure-gpt-4", "api2d-gpt-4",
-                    "chatglm3", "moss", "claude-2"]
+                    "chatglm3", "moss", "claude-2","qwen"]
 # P.S. 其他可用的模型还包括 ["zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613",  "gpt-3.5-random"
 # "spark", "sparkv2", "sparkv3", "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"]
-
+# 如果你需要使用Qwen的本地模型，比如qwen1.8b，那么还需要在request_llms\bridge_qwen.py设置一下模型的路径！
 
 # 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
 MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
diff --git a/request_llms/bridge_qwen.py b/request_llms/bridge_qwen.py
index 85a4d80..d8408d8 100644
--- a/request_llms/bridge_qwen.py
+++ b/request_llms/bridge_qwen.py
@@ -30,7 +30,7 @@ class GetQwenLMHandle(LocalLLMHandle):
         from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 
         with ProxyNetworkActivate('Download_LLM'):
-            model_id = 'qwen/Qwen-7B-Chat'
+            model_id = 'qwen/Qwen-7B-Chat'  #在这里更改路径，如果你已经下载好了的话，同时，别忘记tokenizer
             self._tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen-7B-Chat', trust_remote_code=True, resume_download=True)
             # use fp16
             model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True, fp16=True).eval()
@@ -51,7 +51,7 @@ class GetQwenLMHandle(LocalLLMHandle):
 
         query, max_length, top_p, temperature, history = adaptor(kwargs)
 
-        for response in self._model.chat(self._tokenizer, query, history=history, stream=True):
+        for response in self._model.chat_stream(self._tokenizer, query, history=history):
             yield response
         
     def try_to_import_special_deps(self, **kwargs):