max_new_tokens max_tokens

app.py

@@ -140,7 +140,7 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, How can I help you today?"
             output = client.chat.completions.create(
             formatted_request,
             temperature=temp_value,#0.5
-            max_new_tokens=1000,
+            max_tokens=3000,
             stream=True
         )
             # Create a placeholder for the streaming response