Yossi Synett bc0d26d1de [All Seq2Seq model + CLM models that can be used with EncoderDecoder] Add cross-attention weights to outputs (#8071) ...

* Output cross-attention with decoder attention output

* Update src/transformers/modeling_bert.py

* add cross-attention for t5 and bart as well

* fix tests

* correct typo in docs

* add sylvains and sams comments

* correct typo

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

2020-11-06 19:34:48 +01:00

..

callback.rst

Add AzureML in integrations via dedicated callback (#8062)

2020-10-27 14:21:54 -04:00

configuration.rst

Models doc (#7345)

2020-09-23 13:20:45 -04:00

logging.rst

Doc styling (#8067)

2020-10-26 18:26:02 -04:00

model.rst

Refactoring the generate() function (#6949)

2020-11-03 16:04:22 +01:00

optimizer_schedules.rst

Models doc (#7345)

2020-09-23 13:20:45 -04:00

output.rst

[All Seq2Seq model + CLM models that can be used with EncoderDecoder] Add cross-attention weights to outputs (#8071)

2020-11-06 19:34:48 +01:00

pipelines.rst

Doc styling (#8067)

2020-10-26 18:26:02 -04:00

processors.rst

Doc styling (#8067)

2020-10-26 18:26:02 -04:00

tokenizer.rst

Doc styling (#8067)

2020-10-26 18:26:02 -04:00

trainer.rst

Doc styling (#8067)

2020-10-26 18:26:02 -04:00