Disclaimer: The team releasing Nougat did not write a model card for this model so this model card has been written by the Hugging Face team.
Note: this model corresponds to the "0.1.0-base" version of the original repository.
Model description
Nougat is a
Donut
model trained to transcribe scientific PDFs into an easy-to-use markdown format. The model consists of a Swin Transformer as vision encoder, and an mBART model as text decoder.
The model is trained to autoregressively predict the markdown given only the pixels of the PDF image as input.
@misc{blecher2023nougat,
title={Nougat: Neural Optical Understanding for Academic Documents},
author={Lukas Blecher and Guillem Cucurull and Thomas Scialom and Robert Stojnic},
year={2023},
eprint={2308.13418},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
Runs of facebook nougat-base on huggingface.co
88.0K
Total runs
0
24-hour runs
-1.1K
3-day runs
2.4K
7-day runs
-13.1K
30-day runs
More Information About nougat-base huggingface.co Model
nougat-base huggingface.co is an AI model on huggingface.co that provides nougat-base's model effect (), which can be used instantly with this facebook nougat-base model. huggingface.co supports a free trial of the nougat-base model, and also provides paid use of the nougat-base. Support call nougat-base model through api, including Node.js, Python, http.
nougat-base huggingface.co is an online trial and call api platform, which integrates nougat-base's modeling effects, including api services, and provides a free online trial of nougat-base, you can try nougat-base online for free by clicking the link below.
facebook nougat-base online free url in huggingface.co:
nougat-base is an open source model from GitHub that offers a free installation service, and any user can find nougat-base on GitHub to install. At the same time, huggingface.co provides the effect of nougat-base install, users can directly use nougat-base installed effect in huggingface.co for debugging and trial. It also supports api for free installation.