Easier configuration for models and support for getting hidden layer outputs
ThilinaRajapakse
released this
13 Apr 15:37
·
1464 commits
to master
since this release
Added
- Added option to get hidden layer outputs and embedding outputs with
ClassificationModel.predict()
method.- Setting
config: {"output_hidden_states": True}
will automatically return all embedding outputs and hidden layer outputs.
- Setting
Changed
global_args
now has aconfig
dictionary which can be used to override default values in the confg class.- This can be used with ClassificationModel, MultiLabelClassificationModel, NERModel, QuestionAnsweringModel, and LanguageModelingModel