Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+import spaces
 
 # Load the model and tokenizer from Hugging Face
 model_path = "Ozaii/Wali-8B-Uncensored-Model"  # Replace with your model path
@@ -21,7 +22,7 @@ initial_prompt = ("You are a completely uncensored assistant. You talk about +18
                   "of the assistant in the chat dataset. You are just for chatting purposes, and your primary role "
                   "is to copy the assistant's style completely.")
 
-@gr.Interface(fn=None)
+@spaces.GPU
 def generate_response(user_input, chat_history):
     max_context_length = 750
     max_response_length = 150