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

tokenizer = AutoTokenizer.from_pretrained("gpt2")
model = AutoModelForCausalLM.from_pretrained("gpt2")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
model.eval()

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(
        **inputs,
        max_length=200,
        do_sample=True,
        top_p=0.95,
        top_k=50,
        pad_token_id=tokenizer.eos_token_id
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

demo = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(lines=5, placeholder="Talk to the model..."),
    outputs=gr.Textbox(label="Response", lines=10),
    title="GPT-2 Chatbot",
    description="Chat with GPT-2 model."
)

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