act65

deeperwin

DeepErwin is a python 3.8+ package that implements and optimizes JAX 2.x wave function models for numerical solutions to the multi-electron Schrödinger equation. DeepErwin supports weight-sharing when optimizing wave functions for multiple nuclear geometries and the usage of pre-trained neural network weights to accelerate optimization.

jaxtyping

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

awesome-jax

JAX - A curated list of resources https://github.com/google/jax

sympy2jax

Turn SymPy expressions into trainable JAX expressions.

chemoton

wemake-python-styleguide

The strictest and most opinionated python linter ever!

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

rustgym

Leetcode Solutions in Rust, Advent of Code Solutions in Rust and more

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

nums

A library that translates Python and NumPy to optimized distributed systems code.

book

The Rust Programming Language

Project-Based-Tutorials-in-C

A curated list of project-based tutorials in C

pynauty

Isomorphism testing and automorphisms of graphs

RMG-database

The database of chemical parameters used with Reaction Mechanism Generator

MolecularTransformer

dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

mesh-transformer-jax

Model parallel transformers in JAX and Haiku

surge

A Fast Chemical Graph Generator

mctx

Monte Carlo tree search in JAX

groupoid-rl

balloon-learning-environment

The Balloon Learning Environment - flying stratospheric balloons with deep reinforcement learning.

DeepRLInTheWorld

From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..

rlax

math

The MATH Dataset (NeurIPS 2021)

moses

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

xmanager

A platform for managing machine learning experiments

gym-kuhn-poker

Kuhn poker implemented in accordance to OpenAI gym interface

grinpy

A NetworkX extension for calculating graph invariants.

ieee-pandoc-template

fastT5

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.