Model Alignment is a python library from the PAIR team that enable users to create model prompts through user feedback instead of manual prompt writing and editing. The technique makes use of const…

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

Source code/webpage/demos for the What-If Tool

Spark Implementation of Google Facets Overview https://github.com/PAIR-code/facets

Code for the TCAV ML interpretability project

A WebGL accelerated JavaScript library for training and deploying ML models.

Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).

WebGL-accelerated ML // linear algebra // automatic differentiation for JavaScript.

Visualizations for machine learning datasets

An Open Source Machine Learning Framework for Everyone