- 13 Oct, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 336795303
-
- 12 Oct, 2020 1 commit
-
-
Allen Wang authored
PiperOrigin-RevId: 336709640
-
- 08 Oct, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 336043643
-
- 07 Oct, 2020 2 commits
-
-
Allen Wang authored
PiperOrigin-RevId: 335973329
-
Le Hou authored
PiperOrigin-RevId: 335944731
-
- 06 Oct, 2020 2 commits
-
-
https://github.com/tensorflow/models/issues/9336Chen Chen authored
to support both model and encoder as key in ckpt when exporting to tfhub PiperOrigin-RevId: 335668823
-
Hongkun Yu authored
Add it to export. TODO: move the encoder and decoder layer out to layers/ or decoders/. PiperOrigin-RevId: 335560860
-
- 05 Oct, 2020 1 commit
-
-
Tzu-Wei Sung authored
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/42625 Miss `training` call argument for dropout layer. /cc @tanzhenyu for visibility. Copybara import of the project: -- ba2198fc735a2deca08c68a3c6266d02e01dfe3b by Tzu-Wei Sung <windqaq@gmail.com>: Add training call argument for MultiHeadAttention Remove trailing space PiperOrigin-RevId: 335507127
-
- 03 Oct, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 335226408
-
- 02 Oct, 2020 3 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 335106919
-
Allen Wang authored
PiperOrigin-RevId: 335069348
-
Philip Pham authored
PiperOrigin-RevId: 334950562
-
- 01 Oct, 2020 2 commits
-
-
Allen Wang authored
PiperOrigin-RevId: 334860469
-
Chen Chen authored
PiperOrigin-RevId: 334829363
-
- 30 Sep, 2020 2 commits
-
-
Allen Wang authored
PiperOrigin-RevId: 334642892
-
Chenkai Kuang authored
PiperOrigin-RevId: 334517779
-
- 28 Sep, 2020 2 commits
-
-
Allen Wang authored
PiperOrigin-RevId: 334233893
-
Hongkun Yu authored
PiperOrigin-RevId: 334062074
-
- 27 Sep, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 333979065
-
- 26 Sep, 2020 2 commits
- 25 Sep, 2020 2 commits
- 24 Sep, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 333591143
-
A. Unique TensorFlower authored
Add norm_first to Transformer Scaffold; Add an option in gated_feedword to disable the output layer_norm. PiperOrigin-RevId: 333591020
-
- 23 Sep, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 333314981
-
Ruoxin Sang authored
PiperOrigin-RevId: 333306806
-
- 22 Sep, 2020 5 commits
-
-
Allen Wang authored
PiperOrigin-RevId: 333183470
-
Chen Chen authored
PiperOrigin-RevId: 333163906
-
Hongkun Yu authored
PiperOrigin-RevId: 333019996
-
Chen Chen authored
PiperOrigin-RevId: 333014322
-
Hongkun Yu authored
PiperOrigin-RevId: 332992539
-
- 21 Sep, 2020 6 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 332953126
-
Hongkun Yu authored
PiperOrigin-RevId: 332918217
-
Hongkun Yu authored
PiperOrigin-RevId: 332891157
-
Chen Chen authored
PiperOrigin-RevId: 332806032
-
Chen Chen authored
Remove return_all_encoder_outputs argument from keras_nlp.BertEncoder as it is unused and we will always return all encoder outputs in the returned dict. PiperOrigin-RevId: 332802761
-
Hongkun Yu authored
PiperOrigin-RevId: 332781597
-
- 20 Sep, 2020 1 commit
-
-
Hongkun Yu authored
Migrate all TF-NLP tasks to consume models with dictionary outputs and encoders with dictionary outputs. PiperOrigin-RevId: 332740616
-
- 19 Sep, 2020 1 commit
-
-
Zhenyu Tan authored
PiperOrigin-RevId: 332557462
-