guillaume-be/rust-bert
1
1
Fork 0
mirror of https://github.com/guillaume-be/rust-bert.git synced 2024-09-11 12:55:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Updated changelog

Browse Source
This commit is contained in:
Guillaume Becquin 2021-10-08 16:48:40 +02:00
parent de89e2d165
commit 70c575b552
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
CHANGELOG.md
View File

@ -4,6 +4,7 @@ All notable changes to this project will be documented in this file. The format
## [Unreleased]
## Added
- (BREAKING) Support for `bad_word_ids` generation, allowing to ban a set of word ids for all model supporting text generation
- Support for half-precision mode for all models (reducing memory footprint). A model can be converted to half-precision by calling the `half()` method on the `VarStore` is it currently stored in. Half-precision Torch kernels are not available for CPU (limited to CUDA devices)
## [0.16.0] - 2021-08-24
## Added