- Fixed bug in NERModel.predict() method when `split_on_space=False`. [alexysdussier](https://github.com/alexysdussier)
0.28.60.28.6
Added
- Added multiprocessing support for Question Answering tasks for substantial performance boost where CPU-bound tasks (E.g. prediction especially with long contexts) - Added `multiprocessing_chunksize` (default 500) to `global_args` for finer control over chunking. Usually, the optimal value will be (roughly) `number of examples / process count`.
0.28.50.28.5
Added
- Added `no_save` option to `global_args`. Setting this to `True` will prevent models from being saved to disk. - Added minimal training script for `Seq2Seq` models in the examples directory.
0.28.40.28.4
Fixed
- Fixed potential bugs in loading weights when fine-tuning an ELECTRA language model. Fine-Tuning an ELECTRA language model now requires both `model_name` and `model_type` to be set to `electra`.
0.28.30.28.3
Changed
- Updated `Seq2SeqModel` to use `MarianTokenizer` with MarianMT models. [flozi00](https://github.com/flozi00)