search

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

How to use other types of transformers models? #135

Open heng840 opened 1 year ago

heng840 commented 1 year ago

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 commented 9 months ago

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?