Reduced max tokens further to make sure it accepts a larger question

app.py

@@ -59,7 +59,7 @@ def handle_submit():
             #model="Qwen/Qwen2.5-Coder-32B-Instruct",
             #model="HuggingFaceTB/SmolLM2-1.7B-Instruct",
             messages=messages,
-            max_tokens=1470
+            max_tokens=1000
         )
         
         answer = completion.choices[0].message['content']