How to use other types of transformers models?

[heng840]

Hello! I see that for Text Explainers, the following types are supported:
Sequence Classification Explainer and Pairwise Sequence Classification
MultiLabel Classification Explainer
Zero Shot Classification Explainer
Question Answering Explainer
Token Classification (NER) explainer
Now I want to directly analyze the GPT model, how should I expand it? What additional improvements need to be made?
Thank you!

[hadiasghari]

Hi, I'm also curious if CausalLM tasks (e.g. for GPT2) are already supported, or alternatively if we can help in adding support for them?