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


# Cargar el modelo y el tokenizer
model_id = "DeepESP/gpt2-spanish"
tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=os.getenv("TOKEN"))
model = AutoModelForCausalLM.from_pretrained(model_id, use_auth_token=os.getenv("TOKEN"))

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Crear la interfaz de Gradio
iface = gr.Interface(fn=generate_text, inputs="text", outputs="text", title="Llama-3.2-1B Model")
iface.launch()