Stars
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Friends don't let friends make certain types of data visualization - What are they and why are they bad.
Machine Learning Engineering Open Book
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
Repository for "Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective"
Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena
Fast and memory-efficient exact attention
Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
v objective diffusion inference code for JAX.
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
The most parameter efficient machine learning models on a few popular benchmarks
Google Research
Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways
A DSL for data-driven computational pipelines
A tool for non-coding genomic regions function enrichment analysis based on Regulatory Elements Gene Ontology Annotation (RE-GOA)
Code for "Biological Sequence Design with GFlowNets", 2022
This repository contains the code for our manuscript - 'The evolution, evolvability, and engineering gene regulatory DNA'
Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable,…