Add DPR model (#5279)

* beginning of dpr modeling

* wip

* implement forward

* remove biencoder + better init weights

* export dpr model to embed model for nlp lib

* add new api

* remove old code

* make style

* fix dumb typo

* don't load bert weights

* docs

* docs

* style

* move the `k` parameter

* fix init_weights

* add pretrained configs

* minor

* update config names

* style

* better config

* style

* clean code based on PR comments

* change Dpr to DPR

* fix config

* switch encoder config to a dict

* style

* inheritance -> composition

* add messages in assert startements

* add dpr reader tokenizer

* one tokenizer per model

* fix base_model_prefix

* fix imports

* typo

* add convert script

* docs

* change tokenizers conf names

* style

* change tokenizers conf names

* minor

* minor

* fix wrong names

* minor

* remove unused convert functions

* rename convert script

* use return_tensors in tokenizers

* remove n_questions dim

* move generate logic to tokenizer

* style

* add docs

* docs

* quality

* docs

* add tests

* style

* add tokenization tests

* DPR full tests

* Stay true to the attention mask building

* update docs

* missing param in bert input docs

* docs

* style

Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>
This commit is contained in:
Quentin Lhoest
2020-07-07 14:56:12 +02:00
committed by GitHub
parent d2a9399115
commit fbd8792195
11 changed files with 1531 additions and 3 deletions

View File

@@ -121,7 +121,10 @@ conversion utilities for the following models:
trained using `OPUS <http://opus.nlpl.eu/>`_ pretrained_models data by Jörg Tiedemann.
21. `Longformer <https://github.com/allenai/longformer>`_ (from AllenAI) released with the paper `Longformer: The
Long-Document Transformer <https://arxiv.org/abs/2004.05150>`_ by Iz Beltagy, Matthew E. Peters, and Arman Cohan.
22. `Other community models <https://huggingface.co/models>`_, contributed by the `community
22. `DPR <https://github.com/facebookresearch/DPR>`_ (from Facebook) released with the paper `Dense Passage Retrieval
for Open-Domain Question Answering <https://arxiv.org/abs/2004.04906>`_ by Vladimir Karpukhin, Barlas Oğuz, Sewon
Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.
23. `Other community models <https://huggingface.co/models>`_, contributed by the `community
<https://huggingface.co/users>`_.
.. toctree::
@@ -199,3 +202,4 @@ conversion utilities for the following models:
model_doc/longformer
model_doc/retribert
model_doc/mobilebert
model_doc/dpr