Update app.py

app.py

@@ -1,3 +1,4 @@
++import spaces
 # Load model directly
 import streamlit as st
 from unsloth import FastLanguageModel
@@ -9,6 +10,7 @@ model, tokenizer = FastLanguageModel.from_pretrained(
     load_in_4bit = True,
     token = hf_token, # use one if using gated models like meta-llama/Llama-2-7b-hf
 )
+model.to('cuda')
 
 # alpaca_prompt = You MUST copy from above!
 
@@ -22,6 +24,7 @@ alpaca_prompt = """Below is an instruction that describes a task, paired with an
 ### Response:
 {}"""
 
++@spaces.GPU
   # alpaca_prompt = Copied from above
 c = st.text_input('Enter the contents ')
 FastLanguageModel.for_inference(model) # Enable native 2x faster inference