- 03 Aug, 2022 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 464934071
-
- 14 Jul, 2022 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 460912624
-
- 08 Jun, 2022 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 453749903
-
- 03 May, 2022 2 commits
- 01 Mar, 2022 1 commit
-
-
Jiayu Ye authored
PiperOrigin-RevId: 431722553
-
- 24 Feb, 2022 1 commit
-
-
Jiayu Ye authored
PiperOrigin-RevId: 430740048
-
- 18 Jan, 2022 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 422612138
-
- 07 Jan, 2022 1 commit
-
-
Jiayu Ye authored
PiperOrigin-RevId: 420368411
-
- 03 Dec, 2021 2 commits
- 10 Nov, 2021 1 commit
-
-
Frederick Liu authored
PiperOrigin-RevId: 408970557
-
- 09 Nov, 2021 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 408650343
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 408473818
-
- 03 Nov, 2021 1 commit
-
-
Yuexin Wu authored
PiperOrigin-RevId: 407253800
-
- 02 Nov, 2021 1 commit
-
-
Frederick Liu authored
[bert_encoder] Found a typo in previous experiment and turns out that the checkpoints are compatible even when wrapped in models. PiperOrigin-RevId: 406987505
-
- 29 Oct, 2021 1 commit
-
-
Frederick Liu authored
PiperOrigin-RevId: 406277256
-
- 26 Oct, 2021 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 405548221
-
- 22 Oct, 2021 1 commit
-
-
Yuexin Wu authored
PiperOrigin-RevId: 404920138
-
- 13 Oct, 2021 1 commit
-
-
Yuexin Wu authored
PiperOrigin-RevId: 402882989
-
- 08 Oct, 2021 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 401789124
-
- 07 Oct, 2021 1 commit
-
-
Frederick Liu authored
PiperOrigin-RevId: 401593694
-
- 05 Oct, 2021 1 commit
-
-
Jialu Liu authored
PiperOrigin-RevId: 401000583
-
- 04 Oct, 2021 1 commit
-
-
Yuexin Wu authored
PiperOrigin-RevId: 400837715
-
- 22 Sep, 2021 2 commits
- 16 Sep, 2021 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 397106309
-
- 27 Aug, 2021 1 commit
-
-
Yuexin Wu authored
PiperOrigin-RevId: 393428352
-
- 25 Aug, 2021 2 commits
-
-
Yuexin Wu authored
The current Funnel-Transformer contains only the encoder part and uses 1D-MaxPool for query pooling. PiperOrigin-RevId: 392961143
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 392901555
-
- 18 Aug, 2021 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 391455959
-
- 01 Aug, 2021 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 388118554
-
- 04 Jul, 2021 1 commit
-
-
Frederick Liu authored
PiperOrigin-RevId: 382960239
-
- 06 Jun, 2021 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 377803367
-
Hongkun Yu authored
PiperOrigin-RevId: 377801393
-
- 17 May, 2021 1 commit
-
-
Frederick Liu authored
PiperOrigin-RevId: 374236491
-
- 23 Apr, 2021 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 370159521
-
- 13 Apr, 2021 1 commit
-
-
Reed Wanderman-Milne authored
This replaces symbols in tf.keras.mixed_precision.experimental with the corresponding nonexperimental symbols. In some cases, passing a Policy is replaced with passing a policy name for conciseness. Additionally, for the Shakespeare model, the loss_scale flag is removed, since supporting it with the nonexperimental API is slightly more verbose and it is recommended users use the default loss scale. PiperOrigin-RevId: 368123944
-
- 12 Mar, 2021 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 362613992
-
Chen Chen authored
PiperOrigin-RevId: 362610475
-