app.py

from transformers import pipeline
from gradio import gr
from huggingface_hub import InferenceClient

pipe = pipeline("fill-mask", model="google-bert/bert-base-uncased")

def respond(user_input, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val["role"] == "user":
            messages.append(val)
        if val["role"] == "assistant":
            messages.append(val)

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

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

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

demo = gr.ChatInterface(
    respond,
    inputs=[
        gr.Textbox(placeholder="Type your message here", label="User input"),
        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)"),
    ],
)

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