app.py

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

# Charger le modèle
model_name = "bigcode/starcoder2-15b-instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, 
    torch_dtype=torch.float16,
    device_map="auto"
)

# Fonction pour générer du texte
def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    outputs = model.generate(inputs["input_ids"], max_length=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Interface utilisateur Gradio
interface = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(label="Entrez votre instruction"),
    outputs=gr.Textbox(label="Résultat généré"),
    title="StarCoder2-15B-Instruct"
)

# Lancer l'application
interface.launch()