Update app.py

app.py

@@ -352,7 +352,7 @@ def respond(message, history):
     response = ""
     # Stream response tokens from Hugging Face Inference API
     for chunk in client.chat.completions.create(
-        model="Qwen/Qwen2.5-Coder-32B-Instruct",
+        model="deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
         messages=messages,
         max_tokens=max_tokens,
         stream=True,