Update app.py

app.py

@@ -5,6 +5,7 @@ import numpy as np
 import json
 import os
 import uuid
+import spaces
 import re
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 from peft import PeftModel, AutoPeftModelForCausalLM
@@ -29,6 +30,7 @@ model.eval()
 tokenizer = AutoTokenizer.from_pretrained(lora_path)
 
 # === Updated Generate Answer Function ===
+@spaces.GPU(duration=get_duration)
 def generate_answer(json_data: Dict[str, Any], question: str) -> str:
     """
     Generate answer using the fine-tuned model.