cdpierse / cdpierse/transformers-interpret

How to use classification explainer for custom models?

Open
#145 0 comments 0 reactions 0 assignees View on GitHub
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):
![soal](https://github.com/cdpierse/transformers-interpret/assets/79316338/d5dcc3ae-c5a6-4b97-923c-c62c2894b68d)

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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.