course/pr_1213/es/chapter9/5.md

Integraciones con el Hugging Face Hub[[integrations-with-the-hugging-face-hub]]

Gradio se integra directamente con Hugging Face Hub y Hugging Face Spaces. Puedes cargar demos desde el Hub y desde Spaces con una sola línea de código.

Cargar modelos desde el Hugging Face Hub[[loading-models-from-the-hugging-face-hub]]

import gradio as gr

title = "GPT-J-6B"
description = "Gradio Demo for GPT-J 6B, a transformer model trained using Ben Wang's Mesh Transformer JAX. 'GPT-J' refers to the class of model, while '6B' represents the number of trainable parameters. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
article = "GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model"

gr.Interface.load(
    "huggingface/EleutherAI/gpt-j-6B",
    inputs=gr.Textbox(lines=5, label="Input Text"),
    title=title,
    description=description,
    article=article,
).launch()

Cargar desde Hugging Face Spaces[[loading-from-hugging-face-spaces]]

gr.Interface.load("spaces/abidlabs/remove-bg").launch()

También puedes sobrescribir parámetros al cargar un Space:

gr.Interface.load(
    "spaces/abidlabs/remove-bg", inputs="webcam", title="Remove your webcam background!"
).launch()