Update app.py

app.py

@@ -1,7 +1,6 @@
 import os
 import threading
 import gradio as gr
-import torch
 from transformers import (
     AutoModelForCausalLM,
     AutoTokenizer,
@@ -14,7 +13,6 @@ hf_token = os.environ["HUGGINGFACEHUB_API_TOKEN"]
 # Load tokenizer & model locally
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, token=hf_token)
 model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, token=hf_token)
-model = torch.compile(model)
 model.eval()
 
 def respond(