Skip to content

Commit b6ddb08

Browse files
NielsRoggeLysandreJik
NielsRogge
and
LysandreJik
authored
Add LayoutLMv2 + LayoutXLM (huggingface#12604)
* First commit * Make style * Fix dummy objects * Add Detectron2 config * Add LayoutLMv2 pooler * More improvements, add documentation * More improvements * Add model tests * Add clarification regarding image input * Improve integration test * Fix bug * Fix another bug * Fix another bug * Fix another bug * More improvements * Make more tests pass * Make more tests pass * Improve integration test * Remove gradient checkpointing and add head masking * Add integration test * Add LayoutLMv2ForSequenceClassification to the tests * Add LayoutLMv2ForQuestionAnswering * More improvements * More improvements * Small improvements * Fix _LazyModule * Fix fast tokenizer * Move sync_batch_norm to a separate method * Replace dummies by requires_backends * Move calculation of visual bounding boxes to separate method + update README * Add models to main init * First draft * More improvements * More improvements * More improvements * More improvements * More improvements * Remove is_split_into_words * More improvements * Simply tesseract - no use of pandas anymore * Add LayoutLMv2Processor * Update is_pytesseract_available * Fix bugs * Improve feature extractor * Fix bug * Add print statement * Add truncation of bounding boxes * Add tests for LayoutLMv2FeatureExtractor and LayoutLMv2Tokenizer * Improve tokenizer tests * Make more tokenizer tests pass * Make more tests pass, add integration tests * Finish integration tests * More improvements * More improvements - update API of the tokenizer * More improvements * Remove support for VQA training * Remove some files * Improve feature extractor * Improve documentation and one more tokenizer test * Make quality and small docs improvements * Add batched tests for LayoutLMv2Processor, remove fast tokenizer * Add truncation of labels * Apply suggestions from code review * Improve processor tests * Fix failing tests and add suggestion from code review * Fix tokenizer test * Add detectron2 CI job * Simplify CI job * Comment out non-detectron2 jobs and specify number of processes * Add pip install torchvision * Add durations to see which tests are slow * Fix tokenizer test and make model tests smaller * Frist draft * Use setattr * Possible fix * Proposal with configuration * First draft of fast tokenizer * More improvements * Enable fast tokenizer tests * Make more tests pass * Make more tests pass * More improvements * Addd padding to fast tokenizer * Mkae more tests pass * Make more tests pass * Make all tests pass for fast tokenizer * Make fast tokenizer support overflowing boxes and labels * Add support for overflowing_labels to slow tokenizer * Add support for fast tokenizer to the processor * Update processor tests for both slow and fast tokenizers * Add head models to model mappings * Make style & quality * Remove Detectron2 config file * Add configurable option to label all subwords * Fix test * Skip visual segment embeddings in test * Use ResNet-18 backbone in tests instead of ResNet-101 * Proposal * Re-enable all jobs on CI * Fix installation of tesseract * Fix failing test * Fix index table * Add LayoutXLM doc page, first draft of code examples * Improve documentation a lot * Update expected boxes for Tesseract 4.0.0 beta * Use offsets to create labels instead of checking if they start with ## * Update expected boxes for Tesseract 4.1.1 * Fix conflict * Make variable names cleaner, add docstring, add link to notebooks * Revert "Fix conflict" This reverts commit a9b46ce9afe47ebfcfe7b45e6a121d49e74ef2c5. * Revert to make integration test pass * Apply suggestions from @LysandreJik's review * Address @patrickvonplaten's comments * Remove fixtures DocVQA in favor of dataset on the hub Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>
1 parent 439e7ab commit b6ddb08

28 files changed

+8117
-34
lines changed

‎.circleci/config.yml

Lines changed: 39 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -798,6 +798,44 @@ jobs:
798798
- run: pip install requests
799799
- run: python ./utils/link_tester.py
800800

801+
run_tests_layoutlmv2:
802+
working_directory: ~/transformers
803+
docker:
804+
- image: circleci/python:3.7
805+
environment:
806+
OMP_NUM_THREADS: 1
807+
TRANSFORMERS_IS_CI: yes
808+
resource_class: xlarge
809+
parallelism: 1
810+
steps:
811+
- checkout
812+
- restore_cache:
813+
keys:
814+
- v0.4-torch-{{ checksum "setup.py" }}
815+
- v0.4-{{ checksum "setup.py" }}
816+
- run: sudo apt-get -y update && sudo apt-get install -y libsndfile1-dev
817+
- run: pip install --upgrade pip
818+
- run: pip install .[torch,testing,vision]
819+
- run: pip install torchvision
820+
- run: python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
821+
- run: sudo apt install tesseract-ocr
822+
- run: pip install pytesseract
823+
- save_cache:
824+
key: v0.4-torch-{{ checksum "setup.py" }}
825+
paths:
826+
- '~/.cache/pip'
827+
- run: python utils/tests_fetcher.py | tee test_preparation.txt
828+
- store_artifacts:
829+
path: ~/transformers/test_preparation.txt
830+
- run: |
831+
if [ -f test_list.txt ]; then
832+
python -m pytest -n 1 tests/*layoutlmv2* --dist=loadfile -s --make-reports=tests_layoutlmv2 --durations=100
833+
fi
834+
- store_artifacts:
835+
path: ~/transformers/tests_output.txt
836+
- store_artifacts:
837+
path: ~/transformers/reports
838+
801839
# TPU JOBS
802840
run_examples_tpu:
803841
docker:
@@ -852,6 +890,7 @@ workflows:
852890
- run_tests_onnxruntime
853891
- run_tests_hub
854892
- build_doc
893+
- run_tests_layoutlmv2
855894
- deploy_doc: *workflow_filters
856895
nightly:
857896
triggers:

‎README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -244,6 +244,8 @@ Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.
244244
1. **[Hubert](https://huggingface.co/transformers/model_doc/hubert.html)** (from Facebook) released with the paper [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://arxiv.org/abs/2106.07447) by Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed.
245245
1. **[I-BERT](https://huggingface.co/transformers/model_doc/ibert.html)** (from Berkeley) released with the paper [I-BERT: Integer-only BERT Quantization](https://arxiv.org/abs/2101.01321) by Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer
246246
1. **[LayoutLM](https://huggingface.co/transformers/model_doc/layoutlm.html)** (from Microsoft Research Asia) released with the paper [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://arxiv.org/abs/1912.13318) by Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou.
247+
1. **[LayoutLMv2](https://huggingface.co/transformers/model_doc/layoutlmv2.html)** (from Microsoft Research Asia) released with the paper [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740) by Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou.
248+
1. **[LayoutXLM](https://huggingface.co/transformers/model_doc/layoutlmv2.html)** (from Microsoft Research Asia) released with the paper [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://arxiv.org/abs/2104.08836) by Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Furu Wei.
247249
1. **[LED](https://huggingface.co/transformers/model_doc/led.html)** (from AllenAI) released with the paper [Longformer: The Long-Document Transformer](https://arxiv.org/abs/2004.05150) by Iz Beltagy, Matthew E. Peters, Arman Cohan.
248250
1. **[Longformer](https://huggingface.co/transformers/model_doc/longformer.html)** (from AllenAI) released with the paper [Longformer: The Long-Document Transformer](https://arxiv.org/abs/2004.05150) by Iz Beltagy, Matthew E. Peters, Arman Cohan.
249251
1. **[LUKE](https://huggingface.co/transformers/model_doc/luke.html)** (from Studio Ousia) released with the paper [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://arxiv.org/abs/2010.01057) by Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto.

‎docs/source/index.rst

Lines changed: 43 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -202,99 +202,106 @@ Supported models
202202
34. :doc:`LayoutLM <model_doc/layoutlm>` (from Microsoft Research Asia) released with the paper `LayoutLM: Pre-training
203203
of Text and Layout for Document Image Understanding <https://arxiv.org/abs/1912.13318>`__ by Yiheng Xu, Minghao Li,
204204
Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou.
205-
35. :doc:`LED <model_doc/led>` (from AllenAI) released with the paper `Longformer: The Long-Document Transformer
205+
35. :doc:`LayoutLMv2 <model_doc/layoutlmv2>` (from Microsoft Research Asia) released with the paper `LayoutLMv2:
206+
Multi-modal Pre-training for Visually-Rich Document Understanding <https://arxiv.org/abs/2012.14740>`__ by Yang Xu,
207+
Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min
208+
Zhang, Lidong Zhou.
209+
36. :doc:`LayoutXLM <model_doc/layoutlmv2>` (from Microsoft Research Asia) released with the paper `LayoutXLM:
210+
Multimodal Pre-training for Multilingual Visually-rich Document Understanding <https://arxiv.org/abs/2104.08836>`__
211+
by Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Furu Wei.
212+
37. :doc:`LED <model_doc/led>` (from AllenAI) released with the paper `Longformer: The Long-Document Transformer
206213
<https://arxiv.org/abs/2004.05150>`__ by Iz Beltagy, Matthew E. Peters, Arman Cohan.
207-
36. :doc:`Longformer <model_doc/longformer>` (from AllenAI) released with the paper `Longformer: The Long-Document
214+
38. :doc:`Longformer <model_doc/longformer>` (from AllenAI) released with the paper `Longformer: The Long-Document
208215
Transformer <https://arxiv.org/abs/2004.05150>`__ by Iz Beltagy, Matthew E. Peters, Arman Cohan.
209-
37. :doc:`LUKE <model_doc/luke>` (from Studio Ousia) released with the paper `LUKE: Deep Contextualized Entity
216+
39. :doc:`LUKE <model_doc/luke>` (from Studio Ousia) released with the paper `LUKE: Deep Contextualized Entity
210217
Representations with Entity-aware Self-attention <https://arxiv.org/abs/2010.01057>`__ by Ikuya Yamada, Akari Asai,
211218
Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto.
212-
38. :doc:`LXMERT <model_doc/lxmert>` (from UNC Chapel Hill) released with the paper `LXMERT: Learning Cross-Modality
219+
40. :doc:`LXMERT <model_doc/lxmert>` (from UNC Chapel Hill) released with the paper `LXMERT: Learning Cross-Modality
213220
Encoder Representations from Transformers for Open-Domain Question Answering <https://arxiv.org/abs/1908.07490>`__
214221
by Hao Tan and Mohit Bansal.
215-
39. :doc:`M2M100 <model_doc/m2m_100>` (from Facebook) released with the paper `Beyond English-Centric Multilingual
222+
41. :doc:`M2M100 <model_doc/m2m_100>` (from Facebook) released with the paper `Beyond English-Centric Multilingual
216223
Machine Translation <https://arxiv.org/abs/2010.11125>`__ by by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi
217224
Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman
218225
Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
219-
40. :doc:`MarianMT <model_doc/marian>` Machine translation models trained using `OPUS <http://opus.nlpl.eu/>`__ data by
226+
42. :doc:`MarianMT <model_doc/marian>` Machine translation models trained using `OPUS <http://opus.nlpl.eu/>`__ data by
220227
Jörg Tiedemann. The `Marian Framework <https://marian-nmt.github.io/>`__ is being developed by the Microsoft
221228
Translator Team.
222-
41. :doc:`MBart <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Denoising Pre-training for
229+
43. :doc:`MBart <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Denoising Pre-training for
223230
Neural Machine Translation <https://arxiv.org/abs/2001.08210>`__ by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li,
224231
Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
225-
42. :doc:`MBart-50 <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Translation with Extensible
232+
44. :doc:`MBart-50 <model_doc/mbart>` (from Facebook) released with the paper `Multilingual Translation with Extensible
226233
Multilingual Pretraining and Finetuning <https://arxiv.org/abs/2008.00401>`__ by Yuqing Tang, Chau Tran, Xian Li,
227234
Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.
228-
43. :doc:`Megatron-BERT <model_doc/megatron_bert>` (from NVIDIA) released with the paper `Megatron-LM: Training
235+
45. :doc:`Megatron-BERT <model_doc/megatron_bert>` (from NVIDIA) released with the paper `Megatron-LM: Training
229236
Multi-Billion Parameter Language Models Using Model Parallelism <https://arxiv.org/abs/1909.08053>`__ by Mohammad
230237
Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro.
231-
44. :doc:`Megatron-GPT2 <model_doc/megatron_gpt2>` (from NVIDIA) released with the paper `Megatron-LM: Training
238+
46. :doc:`Megatron-GPT2 <model_doc/megatron_gpt2>` (from NVIDIA) released with the paper `Megatron-LM: Training
232239
Multi-Billion Parameter Language Models Using Model Parallelism <https://arxiv.org/abs/1909.08053>`__ by Mohammad
233240
Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro.
234-
45. :doc:`MPNet <model_doc/mpnet>` (from Microsoft Research) released with the paper `MPNet: Masked and Permuted
241+
47. :doc:`MPNet <model_doc/mpnet>` (from Microsoft Research) released with the paper `MPNet: Masked and Permuted
235242
Pre-training for Language Understanding <https://arxiv.org/abs/2004.09297>`__ by Kaitao Song, Xu Tan, Tao Qin,
236243
Jianfeng Lu, Tie-Yan Liu.
237-
46. :doc:`MT5 <model_doc/mt5>` (from Google AI) released with the paper `mT5: A massively multilingual pre-trained
244+
48. :doc:`MT5 <model_doc/mt5>` (from Google AI) released with the paper `mT5: A massively multilingual pre-trained
238245
text-to-text transformer <https://arxiv.org/abs/2010.11934>`__ by Linting Xue, Noah Constant, Adam Roberts, Mihir
239246
Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel.
240-
47. :doc:`Pegasus <model_doc/pegasus>` (from Google) released with the paper `PEGASUS: Pre-training with Extracted
247+
49. :doc:`Pegasus <model_doc/pegasus>` (from Google) released with the paper `PEGASUS: Pre-training with Extracted
241248
Gap-sentences for Abstractive Summarization <https://arxiv.org/abs/1912.08777>`__> by Jingqing Zhang, Yao Zhao,
242249
Mohammad Saleh and Peter J. Liu.
243-
48. :doc:`ProphetNet <model_doc/prophetnet>` (from Microsoft Research) released with the paper `ProphetNet: Predicting
250+
50. :doc:`ProphetNet <model_doc/prophetnet>` (from Microsoft Research) released with the paper `ProphetNet: Predicting
244251
Future N-gram for Sequence-to-Sequence Pre-training <https://arxiv.org/abs/2001.04063>`__ by Yu Yan, Weizhen Qi,
245252
Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou.
246-
49. :doc:`Reformer <model_doc/reformer>` (from Google Research) released with the paper `Reformer: The Efficient
253+
51. :doc:`Reformer <model_doc/reformer>` (from Google Research) released with the paper `Reformer: The Efficient
247254
Transformer <https://arxiv.org/abs/2001.04451>`__ by Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya.
248-
50. :doc:`RemBERT <model_doc/rembert>` (from Google Research) released with the paper `Rethinking embedding coupling in
255+
52. :doc:`RemBERT <model_doc/rembert>` (from Google Research) released with the paper `Rethinking embedding coupling in
249256
pre-trained language models <https://arxiv.org/pdf/2010.12821.pdf>`__ by Hyung Won Chung, Thibault Févry, Henry
250257
Tsai, M. Johnson, Sebastian Ruder.
251-
51. :doc:`RoBERTa <model_doc/roberta>` (from Facebook), released together with the paper a `Robustly Optimized BERT
258+
53. :doc:`RoBERTa <model_doc/roberta>` (from Facebook), released together with the paper a `Robustly Optimized BERT
252259
Pretraining Approach <https://arxiv.org/abs/1907.11692>`__ by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar
253260
Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
254-
52. :doc:`RoFormer <model_doc/roformer>` (from ZhuiyiTechnology), released together with the paper a `RoFormer:
261+
54. :doc:`RoFormer <model_doc/roformer>` (from ZhuiyiTechnology), released together with the paper a `RoFormer:
255262
Enhanced Transformer with Rotary Position Embedding <https://arxiv.org/pdf/2104.09864v1.pdf>`__ by Jianlin Su and
256263
Yu Lu and Shengfeng Pan and Bo Wen and Yunfeng Liu.
257-
53. :doc:`SpeechToTextTransformer <model_doc/speech_to_text>` (from Facebook), released together with the paper
264+
55. :doc:`SpeechToTextTransformer <model_doc/speech_to_text>` (from Facebook), released together with the paper
258265
`fairseq S2T: Fast Speech-to-Text Modeling with fairseq <https://arxiv.org/abs/2010.05171>`__ by Changhan Wang, Yun
259266
Tang, Xutai Ma, Anne Wu, Dmytro Okhonko, Juan Pino.
260-
54. `Splinter <https://huggingface.co/transformers/master/model_doc/splinter.html>`__ (from Tel Aviv University),
267+
56. `Splinter <https://huggingface.co/transformers/master/model_doc/splinter.html>`__ (from Tel Aviv University),
261268
released together with the paper `Few-Shot Question Answering by Pretraining Span Selection
262269
<https://arxiv.org/abs/2101.00438>`__ by Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson, Omer Levy.
263-
55. :doc:`SqueezeBert <model_doc/squeezebert>` released with the paper `SqueezeBERT: What can computer vision teach NLP
270+
57. :doc:`SqueezeBert <model_doc/squeezebert>` released with the paper `SqueezeBERT: What can computer vision teach NLP
264271
about efficient neural networks? <https://arxiv.org/abs/2006.11316>`__ by Forrest N. Iandola, Albert E. Shaw, Ravi
265272
Krishna, and Kurt W. Keutzer.
266-
56. :doc:`T5 <model_doc/t5>` (from Google AI) released with the paper `Exploring the Limits of Transfer Learning with a
273+
58. :doc:`T5 <model_doc/t5>` (from Google AI) released with the paper `Exploring the Limits of Transfer Learning with a
267274
Unified Text-to-Text Transformer <https://arxiv.org/abs/1910.10683>`__ by Colin Raffel and Noam Shazeer and Adam
268275
Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
269-
57. :doc:`TAPAS <model_doc/tapas>` (from Google AI) released with the paper `TAPAS: Weakly Supervised Table Parsing via
276+
59. :doc:`TAPAS <model_doc/tapas>` (from Google AI) released with the paper `TAPAS: Weakly Supervised Table Parsing via
270277
Pre-training <https://arxiv.org/abs/2004.02349>`__ by Jonathan Herzig, Paweł Krzysztof Nowak, Thomas Müller,
271278
Francesco Piccinno and Julian Martin Eisenschlos.
272-
58. :doc:`Transformer-XL <model_doc/transformerxl>` (from Google/CMU) released with the paper `Transformer-XL:
279+
60. :doc:`Transformer-XL <model_doc/transformerxl>` (from Google/CMU) released with the paper `Transformer-XL:
273280
Attentive Language Models Beyond a Fixed-Length Context <https://arxiv.org/abs/1901.02860>`__ by Zihang Dai*,
274281
Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov.
275-
59. :doc:`Vision Transformer (ViT) <model_doc/vit>` (from Google AI) released with the paper `An Image is Worth 16x16
282+
61. :doc:`Vision Transformer (ViT) <model_doc/vit>` (from Google AI) released with the paper `An Image is Worth 16x16
276283
Words: Transformers for Image Recognition at Scale <https://arxiv.org/abs/2010.11929>`__ by Alexey Dosovitskiy,
277284
Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias
278285
Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
279-
60. :doc:`VisualBERT <model_doc/visual_bert>` (from UCLA NLP) released with the paper `VisualBERT: A Simple and
286+
62. :doc:`VisualBERT <model_doc/visual_bert>` (from UCLA NLP) released with the paper `VisualBERT: A Simple and
280287
Performant Baseline for Vision and Language <https://arxiv.org/pdf/1908.03557>`__ by Liunian Harold Li, Mark
281288
Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang.
282-
61. :doc:`Wav2Vec2 <model_doc/wav2vec2>` (from Facebook AI) released with the paper `wav2vec 2.0: A Framework for
289+
63. :doc:`Wav2Vec2 <model_doc/wav2vec2>` (from Facebook AI) released with the paper `wav2vec 2.0: A Framework for
283290
Self-Supervised Learning of Speech Representations <https://arxiv.org/abs/2006.11477>`__ by Alexei Baevski, Henry
284291
Zhou, Abdelrahman Mohamed, Michael Auli.
285-
62. :doc:`XLM <model_doc/xlm>` (from Facebook) released together with the paper `Cross-lingual Language Model
292+
64. :doc:`XLM <model_doc/xlm>` (from Facebook) released together with the paper `Cross-lingual Language Model
286293
Pretraining <https://arxiv.org/abs/1901.07291>`__ by Guillaume Lample and Alexis Conneau.
287-
63. :doc:`XLM-ProphetNet <model_doc/xlmprophetnet>` (from Microsoft Research) released with the paper `ProphetNet:
294+
65. :doc:`XLM-ProphetNet <model_doc/xlmprophetnet>` (from Microsoft Research) released with the paper `ProphetNet:
288295
Predicting Future N-gram for Sequence-to-Sequence Pre-training <https://arxiv.org/abs/2001.04063>`__ by Yu Yan,
289296
Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang and Ming Zhou.
290-
64. :doc:`XLM-RoBERTa <model_doc/xlmroberta>` (from Facebook AI), released together with the paper `Unsupervised
297+
66. :doc:`XLM-RoBERTa <model_doc/xlmroberta>` (from Facebook AI), released together with the paper `Unsupervised
291298
Cross-lingual Representation Learning at Scale <https://arxiv.org/abs/1911.02116>`__ by Alexis Conneau*, Kartikay
292299
Khandelwal*, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke
293300
Zettlemoyer and Veselin Stoyanov.
294-
65. :doc:`XLNet <model_doc/xlnet>` (from Google/CMU) released with the paper `​XLNet: Generalized Autoregressive
301+
67. :doc:`XLNet <model_doc/xlnet>` (from Google/CMU) released with the paper `​XLNet: Generalized Autoregressive
295302
Pretraining for Language Understanding <https://arxiv.org/abs/1906.08237>`__ by Zhilin Yang*, Zihang Dai*, Yiming
296303
Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le.
297-
66. :doc:`XLSR-Wav2Vec2 <model_doc/xlsr_wav2vec2>` (from Facebook AI) released with the paper `Unsupervised
304+
68. :doc:`XLSR-Wav2Vec2 <model_doc/xlsr_wav2vec2>` (from Facebook AI) released with the paper `Unsupervised
298305
Cross-Lingual Representation Learning For Speech Recognition <https://arxiv.org/abs/2006.13979>`__ by Alexis
299306
Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli.
300307

@@ -372,6 +379,8 @@ Flax), PyTorch, and/or TensorFlow.
372379
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
373380
| LayoutLM | ✅ | ✅ | ✅ | ✅ | ❌ |
374381
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
382+
| LayoutLMv2 | ✅ | ✅ | ✅ | ❌ | ❌ |
383+
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
375384
| LED | ✅ | ✅ | ✅ | ✅ | ❌ |
376385
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
377386
| Longformer | ✅ | ✅ | ✅ | ✅ | ❌ |
@@ -550,6 +559,8 @@ Flax), PyTorch, and/or TensorFlow.
550559
model_doc/herbert
551560
model_doc/ibert
552561
model_doc/layoutlm
562+
model_doc/layoutlmv2
563+
model_doc/layoutxlm
553564
model_doc/led
554565
model_doc/longformer
555566
model_doc/luke

0 commit comments

Comments
 (0)