Adding support to provide custom labels to sequence classification

cdpierse / transformers-interpret

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

Apache License 2.0

1.27k stars 96 forks source link

Adding support to provide custom labels to sequence classification #41

Closed lalitpagaria closed 3 years ago

lalitpagaria commented 3 years ago

To complete https://github.com/cdpierse/transformers-interpret/issues/25

lalitpagaria commented 3 years ago

@cdpierse Can you please review PR

lalitpagaria commented 3 years ago

Thanks for the review. Updated PR with suggested changes ie doc string and black formatting.

cdpierse commented 3 years ago

Amazing work. This is a fantastic PR thanks @lalitpagaria. I'm merging this into dev now and this will be part of the next release 0.4.0 which should hopefully be within the next 2 weeks.

lalitpagaria commented 3 years ago

Thanks @cdpierse for this amazing tool I want to integrate use it with https://github.com/lalitpagaria/obsei So user able to interpret prediction made by AI models like zero shot, sentiment or NER etc.