MBartForConditionalGeneration (#6441)

* add MBartForConditionalGeneration

* style

* rebase and fixes

* add mbart test in TEST_FILES_WITH_NO_COMMON_TESTS

* fix docs

* don't ignore mbart

* doc

* fix mbart fairseq link

* put mbart before bart

* apply doc suggestions

docs/source/index.rst

@@ -126,7 +126,9 @@ conversion utilities for the following models:
     Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.
 23. `Pegasus <https://github.com/google-research/pegasus>`_ (from Google) released with the paper `PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
     <https://arxiv.org/abs/1912.08777>`_ by Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu.
-24. `Other community models <https://huggingface.co/models>`_, contributed by the `community
+24. `MBart <https://github.com/pytorch/fairseq/tree/master/examples/mbart>`_ (from Facebook) released with the paper  `Multilingual Denoising Pre-training for Neural Machine Translation <https://arxiv.org/abs/2001.08210>`_ by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov
+    Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.  
+25. `Other community models <https://huggingface.co/models>`_, contributed by the `community
     <https://huggingface.co/users>`_.
 
 .. toctree::
@@ -208,6 +210,7 @@ conversion utilities for the following models:
     model_doc/mobilebert
     model_doc/dpr
     model_doc/pegasus
+    model_doc/mbart
     internal/modeling_utils
     internal/tokenization_utils
     internal/pipelines_utils

docs/source/model_doc/bart.rst

@@ -49,13 +49,6 @@ BartTokenizer
     :members:
 
 
-MBartTokenizer
-~~~~~~~~~~~~~~~~~~~~~
-
-.. autoclass:: transformers.MBartTokenizer
-    :members: build_inputs_with_special_tokens, prepare_seq2seq_batch
-
-
 
 BartModel
 ~~~~~~~~~~~~~

docs/source/model_doc/mbart.rst

@@ -0,0 +1,37 @@
+MBart
+----------------------------------------------------
+**DISCLAIMER:** If you see something strange,
+file a `Github Issue <https://github.com/huggingface/transformers/issues/new?assignees=&labels=&template=bug-report.md&title>`__ and assign
+@sshleifer
+
+Overview
+~~~~~~~~~~~~~~~~~~~~~
+The MBart model was presented in `Multilingual Denoising Pre-training for Neural Machine Translation <https://arxiv.org/abs/2001.08210>`_ by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov
+Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer. According to the abstract,
+
+MBART is a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective. mBART is one of the first methods for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, while previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text.
+
+The Authors' code can be found `here <https://github.com/pytorch/fairseq/tree/master/examples/mbart>`__
+
+
+MBartConfig
+~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.MBartConfig
+    :members:
+
+
+MBartTokenizer
+~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.MBartTokenizer
+    :members: build_inputs_with_special_tokens, prepare_seq2seq_batch
+
+
+MBartForConditionalGeneration
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.MBartForConditionalGeneration
+    :members: generate, forward
+
+