chrisliu298

CLAIR_and_APO

magpie

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

BetterDisplay

Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!

Open-Reasoning-Tasks

A comprehensive repository of reasoning tasks for LLMs (and beyond)

tamper-resistance

Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"

Awesome-GenAI-Unlearning

circuit-breakers

Improving Alignment and Robustness with Circuit Breakers

nanoGCG

A fast + lightweight implementation of the GCG algorithm in PyTorch

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

awesome-RLAIF

A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)

KnowledgeEditingPapers

Must-read Papers on Knowledge Editing for Large Language Models.

Online-RLHF

A recipe for online RLHF.

LLM101n

LLM101n: Let's build a Storyteller

RWKU

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models

Ice

Powerful menu bar manager for macOS

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

firefoxCSS

A simple, online, minimal, keyboard-centered Firefox CSS theme.

awesome-llm-unlearning

A resource repository for machine unlearning in large language models

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

repeng

A library for making RepE control vectors

transformer-debugger

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

tofu

Landing Page for TOFU

hlb-CIFAR10

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Awesome-Learning-with-Label-Noise

A curated list of resources for Learning with Noisy Labels

awesome-papers

Papers & presentation materials from Hugging Face's internal science day

trl

Train transformer language models with reinforcement learning.