PAIR-code/model-alignment

Stars
6
Rank 2,539,965 (Top 51 %)
Language
Python
License
Apache License 2.0
Created 6 months ago
Updated 6 months ago

PAIR-code/model-alignment

PAIR-code

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

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 constitutional principles to align prompts to users' desired values.

facets

Visualizations for machine learning datasets

Jupyter Notebook

lit

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

saliency

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

Jupyter Notebook

what-if-tool

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

umap-js

JavaScript implementation of UMAP

llm-comparator

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

knowyourdata

A tool to help researchers and product teams understand datasets with the goal of improving data quality, and mitigating fairness and bias issues.

wordcraft

✨✍️ Wordcraft is an AI-powered text editor with an emphasis on short story writing

datacardsplaybook

The Data Cards Playbook helps dataset producers and publishers adopt a people-centered approach to transparency in dataset documentation.

scatter-gl

Interactive 3D / 2D webgl-accelerated scatter plot point renderer

understanding-umap

Understanding the theory behind UMAP

federated-learning

Federated learning experiment using TensorFlow.js

interpretability

PAIR.withgoogle.com and friend's work on interpretability methods

ai-explorables

https://pair.withgoogle.com/explorables/

Jupyter Notebook

cococo

𝄡 Collaborative Convolutional Counterpoint

cam-scroller

Cam Scroller is an open-source Chrome extension that uses your webcam and deeplearn.js to enable scrolling through webpages using custom gestures that you define.

font-explorer

Font latent space explorer using tensorflow.js

clinical-vis

A javascript medical record visualization (https://arxiv.org/abs/1810.05798)

megaplot

depth-maps-art-and-illusions

pair-code.github.io

farsight

In situ interactive widgets for responsible AI 🌱

tiny-transformers

Jupyter Notebook

recommendation-rudders

covid19_symptom_dataset

thehardway

Supplementary code repository to accompany Tic-Tac-Toe the Hard Way podcast

jax-recommenders

autonotes

AutoNotes is an experimental prototype for AI-powered notetaking, with features including hierarchical tagging, "chat with your notes," and highlights.

book-viz

Visualizing multilevel structure in books with sentence embeddings.

Jupyter Notebook

waterfall-of-meaning

deliberate-lab

Platform for running online research experiments on human + LLM group dynamics.

deeplearnjs-legacy-loader

Deprecated: Legacy TensorFlow model loader for deeplearn.js

colormap

adversarial-nibbler-vis

An interactive visualization interface for exploring and analyzing the Adversarial Nibbler dataset

auto-histograms

ml-vis-experiments

Jupyter Notebook

deeplearnjs-docs