druidowm
I am Owen Dugan, a physics major at MIT (class of 2025). I research at the intersection of AI and Physics.
druidowm's Stars
tinygrad/tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
quanta-fine-tuning/quanta
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
OpenDevin/OpenDevin
🐚 OpenDevin: Code Less, Make More
CUAI/Neural-Manifold-Ordinary-Differential-Equations
[NeurIPS 2020] Neural Manifold Ordinary Differential Equations (https://arxiv.org/abs/2006.10254)
n2cholas/awesome-jax
JAX - A curated list of resources https://github.com/google/jax
Matematija/auto-xc
Automatic differentiation tools for interfacing custom density functionals with libXC.
probml/dynamax
State Space Models library in JAX
patrick-kidger/optimistix
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
patrick-kidger/lineax
Linear solvers in JAX and Equinox. https://docs.kidger.site/lineax
stanford-crfm/haliax
Named Tensors for Legible Deep Learning in JAX
google-deepmind/kfac-jax
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
FLAIROx/JaxMARL
Multi-Agent Reinforcement Learning with JAX
feizc/Visual-LLaMA
Open LLaMA Eyes to See the World
patrick-kidger/quax
Multiple dispatch over abstract array types in JAX.
tysam-code/hlb-CIFAR10
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
abetlen/llama-cpp-python
Python bindings for llama.cpp
stanford-crfm/levanter
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
google-research/bert
TensorFlow code and pre-trained models for BERT
google-research/jax3d
google-research/t5x
helblazer811/ManimML
ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.
google-deepmind/distrax
CodeEditApp/CodeEdit
CodeEdit App for macOS – Elevate your code editing experience. Open source, free forever.
cavalab/srbench
A living benchmark framework for symbolic regression
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
blackjax-devs/blackjax
BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.
CompVis/stable-diffusion
A latent text-to-image diffusion model
janosh/awesome-normalizing-flows
Awesome resources on normalizing flows.
jwasham/coding-interview-university
A complete computer science study plan to become a software engineer.
sindresorhus/awesome
😎 Awesome lists about all kinds of interesting topics