DSPy: The framework for programming—not prompting—foundation models

Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions

Puzzles for learning Triton

Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.

Official code for "Large Language Models Are Reasoning Teachers", ACL 2023

A guidance language for controlling large language models.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Schedule and Syllabus for Human-Centered Machine learning.

Inference algorithms for models based on Luce's choice axiom

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

List of research around modern boardgames.

AI Data Management & Evaluation Platform

🦜🔗 Build context-aware reasoning applications

🥤🧑🏻‍🚀Code and dataset for our EMNLP 2023 paper - "SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization"

Repository for the Bias Benchmark for QA dataset.

Accompanying repo for the RLPrompt paper

Laboratory automation for the behavioral and social sciences; human culture on a chip.

A highly efficient implementation of Gaussian Processes in PyTorch

Bayesian optimization in PyTorch

Break the linear presentation of Jupyter Notebooks with sticky cells!

Co-op codenames app (ala Codenames Duet)

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

🎓 Advice and resources for thriving and surviving graduate school

ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the u…

Play codenames online