nielsr HF staff commited on
Commit
414f455
1 Parent(s): 9f0b485

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -0
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - vision
5
+ ---
6
+
7
+ # Donut (base-sized model, pre-trained only)
8
+
9
+ Donut model pre-trained-only. It was introduced in the paper [OCR-free Document Understanding Transformer](https://arxiv.org/abs/2111.15664) by Geewok et al. and first released in [this repository](https://github.com/clovaai/donut).
10
+ 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.
11
+
12
+ ## Model description
13
+
14
+ 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.
15
+
16
+ ## Intended uses & limitations
17
+
18
+ You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=google/vit) to look for
19
+ fine-tuned versions on a task that interests you.
20
+
21
+ ### How to use
22
+
23
+ We refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/donut) which includes code examples.
24
+
25
+ ### BibTeX entry and citation info
26
+
27
+ ```bibtex
28
+ @article{DBLP:journals/corr/abs-2111-15664,
29
+ author = {Geewook Kim and
30
+ Teakgyu Hong and
31
+ Moonbin Yim and
32
+ Jinyoung Park and
33
+ Jinyeong Yim and
34
+ Wonseok Hwang and
35
+ Sangdoo Yun and
36
+ Dongyoon Han and
37
+ Seunghyun Park},
38
+ title = {Donut: Document Understanding Transformer without {OCR}},
39
+ journal = {CoRR},
40
+ volume = {abs/2111.15664},
41
+ year = {2021},
42
+ url = {https://arxiv.org/abs/2111.15664},
43
+ eprinttype = {arXiv},
44
+ eprint = {2111.15664},
45
+ timestamp = {Thu, 02 Dec 2021 10:50:44 +0100},
46
+ biburl = {https://dblp.org/rec/journals/corr/abs-2111-15664.bib},
47
+ bibsource = {dblp computer science bibliography, https://dblp.org}
48
+ }
49
+ ```