app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("Qwen/Qwen2.5-7B-Instruct")


def respond(message, history):
    messages = [{"role": "system", "content": "You are a friendly chatbot"}]

    if history:
        messages.extend(history)

    messages.append({"role": "user", "content": message})

    response = ""

    for chunk in client.chat_completion(
        messages,
        max_tokens=256,
        temperature=0.7,
        top_p=0.9,
        stream=True,
    ):
        token = chunk.choices[0].delta.content
        response += token
        yield response

chatbot = gr.ChatInterface(respond)
chatbot.launch(debug=True)