Update app.py

app.py

@@ -2,11 +2,12 @@ import re
 from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM
 
+
+@spaces.GPU
 config = PeftConfig.from_pretrained("FlawedLLM/BhashiniLLM")
 base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit")
 model = PeftModel.from_pretrained(base_model, "FlawedLLM/BhashiniLLM")
 tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
-@spaces.GPU
 def chunk_it(input_command):
     inputs = tokenizer(
     [