%%writefile app.py

import torch
import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

MODEL_NAME = "google/flan-t5-small"
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
…    )

if __name__ == "__main__":
    demo.launch()