Update app.py

app.py

@@ -1,7 +1,7 @@
 # main.py
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-
+import torch
 # Load model and tokenizer
 model_name = "meta-llama/Llama-2-7b-chat-hf"
 print("started loading model")