changed llm model test

app.py

@@ -4,6 +4,7 @@ from typing import List, Dict, Tuple
 from flask import Flask, request, jsonify
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import threading
+import torch
 
 # Define the API URL to use the internal server
 API_URL = "http://localhost:5000/chat"