SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add DeBERTa model (#5929)

Browse Source 
* Add DeBERTa model

* Remove dependency of deberta

* Address comments

* Patch DeBERTa
Documentation
Style

* Add final tests

* Style

* Enable tests + nitpicks

* position IDs

* BERT -> DeBERTa

* Quality

* Style

* Tokenization

* Last updates.

* @patrickvonplaten's comments

* Not everything can be a copy

* Apply most of @sgugger's review

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Last reviews

* DeBERTa -> Deberta

Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
Pengcheng He
2020-09-30 04:07:30 -07:00
committed by GitHub
parent 44a93c981f
commit 7a0cf0ec93
16 changed files with 2350 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
docs/source/model_doc/deberta.rst Normal file
View File

@@ -0,0 +1,62 @@
DeBERTa
----------------------------------------------------
Overview
~~~~~~~~~~~~~~~~~~~~~
The DeBERTa model was proposed in `DeBERTa: Decoding-enhanced BERT with Disentangled Attention <https://arxiv.org/abs/2006.03654>`__
by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen
It is based on Google's BERT model released in 2018 and Facebook's RoBERTa model released in 2019.
It builds on RoBERTa with disentangled attention and enhanced mask decoder training with half of the data used in RoBERTa.
The abstract from the paper is the following:
*Recent progress in pre-trained neural language models has significantly improved the performance of many natural language processing (NLP) tasks.
In this paper we propose a new model architecture DeBERTa (Decoding-enhanced BERT with disentangled attention) that improves the BERT and RoBERTa
models using two novel techniques. The first is the disentangled attention mechanism, where each word is represented using two vectors that encode
its content and position, respectively, and the attention weights among words are computed using disentangled matrices on their contents and
relative positions. Second, an enhanced mask decoder is used to replace the output softmax layer to predict the masked tokens for model pretraining.
We show that these two techniques significantly improve the efficiency of model pre-training and performance of downstream tasks. Compared to
RoBERTa-Large, a DeBERTa model trained on half of the training data performs consistently better on a wide range of NLP tasks, achieving improvements
on MNLI by +0.9% (90.2% vs. 91.1%), on SQuAD v2.0 by +2.3% (88.4% vs. 90.7%) and RACE by +3.6% (83.2% vs. 86.8%). The DeBERTa code and pre-trained
models will be made publicly available at https://github.com/microsoft/DeBERTa.*
The original code can be found `here <https://github.com/microsoft/DeBERTa>`__.
DebertaConfig
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.DebertaConfig
:members:
DebertaTokenizer
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.DebertaTokenizer
:members: build_inputs_with_special_tokens, get_special_tokens_mask,
create_token_type_ids_from_sequences, save_vocabulary
DebertaModel
~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.DebertaModel
:members:
DebertaPreTrainedModel
~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.DebertaPreTrainedModel
:members:
DebertaForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.DebertaForSequenceClassification
:members: