app.py

import gradio as gr
from transformers import pipeline

# Load the model
model = pipeline("text-generation", model="karthikqnq/qnqgpt2")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Construct the prompt from history and current message
    prompt = system_message + "\n\n"
    for user_msg, assistant_msg in history:
        if user_msg:
            prompt += f"User: {user_msg}\nAssistant: {assistant_msg}\n"
    prompt += f"User: {message}\nAssistant: "

    # Generate response
    response = model(
        prompt,
        max_length=max_tokens,
        temperature=temperature,
        top_p=top_p,
        do_sample=True,
        num_return_sequences=1
    )[0]['generated_text']

    # Extract only the assistant's response
    try:
        assistant_response = response.split("Assistant: ")[-1].strip()
    except:
        assistant_response = response

    return assistant_response

# Create the Gradio interface
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(
            value="You are a friendly Chatbot.", 
            label="System message"
        ),
        gr.Slider(
            minimum=1,
            maximum=2048,
            value=512,
            step=1,
            label="Max new tokens"
        ),
        gr.Slider(
            minimum=0.1,
            maximum=4.0,
            value=0.7,
            step=0.1,
            label="Temperature"
        ),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)"
        ),
    ],
    title="QnQ GPT-2 Chatbot",
    description="A chatbot powered by the QnQ GPT-2 model"
)

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