app.py

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

# Load free public model
model_name = "google/flan-t5-small"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

def chat(prompt):
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids
    with torch.no_grad():
        outputs = model.generate(input_ids, max_new_tokens=200)
    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return reply

demo = gr.Interface(fn=chat, inputs="text", outputs="text", title="FLAN-T5 Chatbot")

demo.launch()