Update app.py

app.py

@@ -49,7 +49,7 @@ def respond(
     # Generate a response
     chat_history_ids = model.generate(
         input_ids,
-        max_length=max_tokens,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
         pad_token_id=tokenizer.eos_token_id,