---
tags:
- document-understading
- endpoints-template
library_name: generic
---

# Deploy a Space as inference Endpoint

_This is a fork of the [naver-clova-ix/donut-base-finetuned-cord-v2](https://huggingface.co/spaces/naver-clova-ix/donut-base-finetuned-cord-v2) Space_

This repository implements a custom container for 🤗 Inference Endpoints using a gradio space.

To use deploy this model as an Inference Endpoint, you have to select Custom as task and a custom image. The image you can use is `philschmid/gradio-api:cpu` for CPU and `philschmid/gradio-api:gpu` for GPU images. The PORT to select is `7860`.

 If you want to use the UI with the inference Endpoint, you have to select as endpoint type `public` and add [auth through gradio](https://gradio.app/docs/#launch-header)