v0.1.9

• Add fixes for GPU support.
• word_attributions are now calculated using decoded input_ids rather than original input text. This is due to certain encoding methods like Byte-Pair-Encoding (BPE) breaking words into byte pairs. Captum's attributions are on byte pair level not word level. Rather than averaging the byte pairs back into the original word I am choosing to just return byte pairs in the list.

v0.1.5

Small patch:

• Fix windows utf-8 bug in setup.py

Initial Release v0.1.4

• Sequence classification support
• Word attribution and visualization of attributions
• Use of layer integrated gradients as attribution method
• > 90% test coverage