Patrick von Platen 56ee2560be [Longformer] Better handling of global attention mask vs local attention mask (#4672) ...

* better api

* improve automatic setting of global attention mask

* fix longformer bug

* fix global attention mask in test

* fix global attn mask flatten

* fix slow tests

* update docstring

* update docs and make more robust

* improve attention mask

2020-05-29 17:58:42 +02:00

..

albert.rst

[Longformer] Multiple choice for longformer (#4645)

2020-05-29 13:46:08 +02:00

auto.rst

adding in the doc

2020-01-27 14:27:07 -05:00

bart.rst

[Marian] documentation and AutoModel support (#4152)

2020-05-10 13:54:57 -04:00

bert.rst

Cleanup fast tokenizers integration (#3706)

2020-04-18 13:43:57 +02:00

camembert.rst

[Docs] Add DialoGPT (#3755)

2020-04-16 09:04:32 +02:00

ctrl.rst

[Docs] Add DialoGPT (#3755)

2020-04-16 09:04:32 +02:00

dialogpt.rst

add dialogpt training tips (#3996)

2020-04-28 14:32:31 +02:00

distilbert.rst

Cleanup fast tokenizers integration (#3706)

2020-04-18 13:43:57 +02:00

electra.rst

Cleanup fast tokenizers integration (#3706)

2020-04-18 13:43:57 +02:00

encoderdecoder.rst

Clean Encoder-Decoder models with Bart/T5-like API and add generate possibility (#3383)

2020-04-28 15:11:09 +02:00

flaubert.rst

[Docs] Add DialoGPT (#3755)

2020-04-16 09:04:32 +02:00

gpt2.rst

Cleanup fast tokenizers integration (#3706)

2020-04-18 13:43:57 +02:00

gpt.rst

Cleanup fast tokenizers integration (#3706)

2020-04-18 13:43:57 +02:00

longformer.rst

[Longformer] Better handling of global attention mask vs local attention mask (#4672)

2020-05-29 17:58:42 +02:00

marian.rst

[Marian Fixes] prevent predicting pad_token_id before softmax, support language codes, name multilingual models (#4290)

2020-05-13 17:29:41 -04:00

reformer.rst

[Reformer] fix reformer num buckets (#4564)

2020-05-25 16:04:45 -04:00

roberta.rst

[Longformer] Multiple choice for longformer (#4645)

2020-05-29 13:46:08 +02:00

t5.rst

Fix t5 doc typos (#3978)

2020-04-27 18:27:15 +02:00

transformerxl.rst

Cleanup fast tokenizers integration (#3706)

2020-04-18 13:43:57 +02:00

xlm.rst

[Docs] Add DialoGPT (#3755)

2020-04-16 09:04:32 +02:00

xlmroberta.rst

[Docs] Add DialoGPT (#3755)

2020-04-16 09:04:32 +02:00

xlnet.rst

[doc] Fix broken links + remove crazy big notebook

2020-05-07 18:44:18 -04:00