This repository was archived by the owner on Jul 7, 2023. It is now read-only.
v1.2.3
- Transformer now supports fast decoding! The decoding path used to recompute the entire sequence on each additional timestep, but now caches as it goes.
- We now support
SavedModelexports - New more thorough documentation
- Travis builds for all PRs and commits for Python 2 and 3!
- The decoding flags for
t2t_decoderhave all been merged into a singleHParamsobject that can be modified with the flag--decode_hparams - Various feature additions, bug fixes, and improvements
- Note: Parameter checkpoints for the Transformer model may be broken because of a bug with variable sharing in
layer_norm