app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("gpt2")
model = AutoModelForCausalLM.from_pretrained("gpt2")

def generate_response(message: str, history: list) -> str:
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(inputs.input_ids, max_length=50)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

gr.ChatInterface(generate_response).launch()