amazon / bort
Other16018Updated May 29, 2025
Downloads
160
Likes
18
Last updated
May 29, 2025
License
Not available
BORT is a highly compressed version of bert-large that is up to 10 times faster at inference. The model is an optimal sub-architecture of bert-large that was found using neural architecture search.
Tasks & library
- fill mask
- transformers
Tags
- transformers
- pytorch
- tf
- jax
- bert
- fill-mask
Technical specifications
ParametersNot available
Librarytransformers
LanguagesNot available
LicenseNot available
