Update app.py

app.py

@@ -6,7 +6,7 @@ api_key = os.environ.get('qwen_API_KEY')
 """
 For more information on huggingface_hub Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", token=api_key)
+client = InferenceClient( token=api_key)
 
 def respond(
     message,
@@ -30,6 +30,7 @@ def respond(
 
     for message in client.chat_completion(
         messages,
+        model="deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
@@ -69,5 +70,5 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.queue(default_concurrency_limit=80)
-    demo.launch(max_threads=80)
+    demo.queue(default_concurrency_limit=60)
+    demo.launch(max_threads=60)