Update app.py

app.py

@@ -3,7 +3,6 @@ from llama_cpp import Llama
 from concurrent.futures import ThreadPoolExecutor, as_completed
 import re
 import httpx
-from spaces import GPU
 import asyncio
 import gradio as gr
 
@@ -82,7 +81,7 @@ def remove_duplicates(text):
             seen_lines.add(line)
     return '\n'.join(unique_lines)
 
-@GPU(duration=0)
+
 def generate_model_response(model, inputs):
     try:
         response = model(inputs)