cdpierse / cdpierse/transformers-interpret
How to use classification explainer for custom models?
Open
- Dominant language
- Jupyter Notebook
- Stars
- 1.4k
- Forks
- 99
- PR merge metrics
- No merged PRs in 30d
Description
I've just been introduced to your package (it is so helpful).
I have a question regarding the classification explainer. I've fine-tuned a distilbert model on a specific dataset with my own designed classifier (several fc layers) on top of that (so, my model is not in the pretrained bert models):

when I try to use the package to interpret outcomes, it gives this error:
`'Distilbert' object has no attribute 'config'.`
How should I fix that?
Thanks
Contributor guide
Assessment
This issue has not been assessed yet.