Scalable RL solution for advanced reasoning of language models

Friends of OLMo and their links.

🟣 LLMs interview questions and answers to help you prepare for your next machine learning and data science interview in 2024.

veRL: Volcano Engine Reinforcement Learning for LLM

Best practices & guides on how to write distributed pytorch training code

Skywork Reward Model Series

Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment

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

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!

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

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

Improving Alignment and Robustness with Circuit Breakers

A fast + lightweight implementation of the GCG algorithm in PyTorch

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

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

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

A recipe for online RLHF and online iterative DPO.

LLM101n: Let's build a Storyteller

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024

Powerful menu bar manager for macOS

Universal and Transferable Attacks on Aligned Language Models

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

A resource repository for machine unlearning in large language models

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

A library for making RepE control vectors

Reference implementation for DPO (Direct Preference Optimization)

Representation Engineering: A Top-Down Approach to AI Transparency

Landing Page for TOFU