SAVRN
Search Contact SAVRN

Open-weight model · Document question answering

donut-base-finetuned-docvqa

by NAVER CLOVA INFORMATION EXTRACTION naver-clova-ix/donut-base-finetuned-docvqa

Donut model fine-tuned on DocVQA. It was introduced in the paper OCR-free Document Understanding Transformer by Geewok et al. and first released in this repository.

Parameters
Context
Weights803.4 MB
Licensemit
AccessOpen weights
Monthly Downloads24.3k

Model Card

By NAVER CLOVA INFORMATION EXTRACTION, published under mit, revision b19d2e332684.

Donut model fine-tuned on DocVQA. It was introduced in the paper OCR-free Document Understanding Transformer by Geewok et al. and first released in this repository. Disclaimer: The team releasing Donut did not write a model card for this model so this model card has been written by the Hugging Face team. Donut consists of a vision encoder (Swin Transformer) and a text decoder (BART). Given an image, the encoder first encodes the image into a tensor of embeddings (of shape batchsize, seqlen, hiddensize), after which the decoder autoregressively generates text, conditioned on the encoding of the encoder. This model is fine-tuned on DocVQA, a document visual question answering dataset. We…

Read NAVER CLOVA INFORMATION EXTRACTION's full model card

Donut (base-sized model, fine-tuned on DocVQA)

Donut model fine-tuned on DocVQA. It was introduced in the paper OCR-free Document Understanding Transformer by Geewok et al. and first released in this repository.

Disclaimer: The team releasing Donut did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

Donut consists of a vision encoder (Swin Transformer) and a text decoder (BART). Given an image, the encoder first encodes the image into a tensor of embeddings (of shape batch_size, seq_len, hidden_size), after which the decoder autoregressively generates text, conditioned on the encoding of the encoder.

Intended uses & limitations

This model is fine-tuned on DocVQA, a document visual question answering dataset.

We refer to the documentation which includes code examples.

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2111-15664,
  author    = {Geewook Kim and
               Teakgyu Hong and
               Moonbin Yim and
               Jinyoung Park and
               Jinyeong Yim and
               Wonseok Hwang and
               Sangdoo Yun and
               Dongyoon Han and
               Seunghyun Park},
  title     = {Donut: Document Understanding Transformer without {OCR}},
  journal   = {CoRR},
  volume    = {abs/2111.15664},
  year      = {2021},
  url       = {https://arxiv.org/abs/2111.15664},
  eprinttype = {arXiv},
  eprint    = {2111.15664},
  timestamp = {Thu, 02 Dec 2021 10:50:44 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2111-15664.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Configuration

Architecture
VisionEncoderDecoderModel
Stored precision
float32
Model type
vision-encoder-decoder

Identity and Version

Repository
naver-clova-ix/donut-base-finetuned-docvqa
Publisher
NAVER CLOVA INFORMATION EXTRACTION
Task
Document question answering
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
b19d2e332684b0e2d35d9144ce34047767335cf8
First published
2022-07-19
Last updated
2024-03-09

Files and Weights

11 files, 808.7 MB in total. The weights are 1 file totalling 803.4 MB in bin.

Weights1 file · 803.4 MB
Configuration4 files · 5.8 KB
Tokenizer2 files · 4.0 MB
Documentation1 file · 2.4 KB
Other1 file · 1.3 MB
Repository2 files · 1.4 KB
Every file
FileTypeSizeSHA-256
pytorch_model.binWeights803.4 MB 0783ed4980d0
added_tokens.jsonConfiguration229 B
config.jsonConfiguration4.7 KB
preprocessor_config.jsonConfiguration359 B
special_tokens_map.jsonConfiguration478 B
README.mdDocumentation2.4 KB
sentencepiece.bpe.modelOther1.3 MB cb9e3dce4c32
.gitattributesRepository1.3 KB
.gitignoreRepository10 B
tokenizer.jsonTokenizer4.0 MB
tokenizer_config.jsonTokenizer535 B

License and Download

License
mit
Access
Open weights, no gate
Download size
803.4 MB
Download from NAVER CLOVA INFORMATION EXTRACTION

Released by NAVER CLOVA INFORMATION EXTRACTION through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published803.4 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About donut-base-finetuned-docvqa

Can I use donut-base-finetuned-docvqa commercially?

Yes. donut-base-finetuned-docvqa is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.