Gradient-based LLM attribution in tutorial + LLM attribution type annotations

pytorch / captum

Model interpretability and understanding for PyTorch

https://captum.ai

BSD 3-Clause "New" or "Revised" License

4.93k stars 499 forks source link

Gradient-based LLM attribution in tutorial + LLM attribution type annotations #1332

Closed craymichael closed 3 months ago

craymichael commented 3 months ago

Summary: Add gradient-based LLM attribution to the tutorial notebook. Addresses https://github.com/pytorch/captum/issues/1237. Additionally, add more type annotations to llm_attr.py.

Differential Revision: D61460934

facebook-github-bot commented 3 months ago

This pull request was exported from Phabricator. Differential Revision: D61460934