app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

MODEL_NAME = "Ronaldodev/llama"

# Charger modèle et tokenizer UNE SEULE FOIS
print("Chargement du modèle...")
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        **inputs,
        max_new_tokens=200,
        do_sample=True,
        temperature=0.7
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(
    fn=chat,
    inputs=gr.Textbox(lines=5, placeholder="Écris ton message ici..."),
    outputs=gr.Textbox(),
    title="Assistant IA (Llama 3.2 1B CPU)",
)

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