Update app.py

app.py

@@ -1,5 +1,3 @@
-# LoRA Inference Gradio Space Demo
-
 import spaces
 import gradio as gr
 from peft import PeftModel
@@ -22,6 +20,7 @@ model = PeftModel.from_pretrained(
 # Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained("unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit")
 
+@spaces.GPU
 def generate_response(prompt):
     reasoning_prompt = (
         "Answer the following question and explain your reasoning step by step.\n"