Update app.py

app.py

@@ -2,6 +2,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 import torch
 import gradio as gr
+from huggingface_hub import spaces
 
 # --- Model Loading ---
 base_model_id = "unsloth/Meta-Llama-3.1-8B"
@@ -22,6 +23,7 @@ except Exception as e:
     tokenizer = None
 
 # --- Generation Function ---
+@spaces.GPU
 def generate_response(information, input_text):
     if model is None or tokenizer is None:
         return "Model not loaded. Please check the logs."