app.py

import os
import gradio as gr
from huggingface_hub import InferenceClient


hf_token = os.environ["HUGGINGFACEHUB_API_TOKEN"]
client = InferenceClient("MaxLSB/LeCarnet-8M", token=hf_token)


def respond(
    prompt,
    chat_history,
    max_tokens,
    temperature,
    top_p,
):
    response = ""

    for token in client.text_generation(
        prompt=prompt,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=True,
    ):
        response += token
        yield response


demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Slider(minimum=1, maximum=512, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, 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()