app.py

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

model_name = "Houzeric/mini-gpt-french"

tokenizer = AutoTokenizer.from_pretrained("camembert-base")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    trust_remote_code=True
)


def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    prompt = message 
    
    inputs = tokenizer(prompt, return_tensors="pt")
    
    inputs = {k: v.to(model.device) for k, v in inputs.items()}

    outputs = model.generate(
        **inputs,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        do_sample=True
    )

    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

    input_length = inputs["input_ids"].shape[1]
    generated_tokens = outputs[0][input_length:]
    response_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
    
    return response_text

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
chatbot = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=100, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.8, 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 = chatbot
    demo.launch()