- Sydney, Australia
- @lucia_quirke
Stars
Scores tweets on inflammatory-ness; rewords the bad ones.
An extremely fast Python package and project manager, written in Rust.
Python 3.8+ toolbox for submitting jobs to Slurm
Muon optimizer: +~30% sample efficiency with <3% wallclock overhead
Machine Learning Engineering Open Book
Papers from the computer science community to read and discuss.
Multi-Joint dynamics with Contact. A general purpose physics simulator.
Preference-based reinforcement learning in PyTorch and JAX with a browser-based GUI.
Code for The Grammar-Learning Trajectories of Neural Language Models
Understanding how features learned by neural networks evolve throughout training
A C++ library providing fast language model queries in compressed space.
GPU programming related news and material links
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
Erasing concepts from neural representations with provable guarantees
Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2022)
Using Google N-Gram Data and get the top 10 bigrams by Average Usage per book - PIG/AWS
Sparse probing paper full code.
[NeurIPS'22] Tokenized Graph Transformer (TokenGT), in PyTorch
Mechanistic Interpretability Visualizations using React
Tools for understanding how transformer predictions are built layer-by-layer
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
A library for mechanistic interpretability of GPT-style language models
A Python library for creating and solving mazes.