louissmit
Follow
Stars
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Loopy belief propagation for factor graphs on discrete variables in JAX
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
A pure-functional implementation of a machine learning transformer model in Python/JAX
☠️ Common Security Exploits and Protections on Solana
Pretrained Language Models for Korean
Open Sauce Fonts is a font super family that I developed for Creative Sauce's internal type system. It is a compact typeface that is optimised for better viewing small text on screen and print. Ope…
🐻 Bear necessities for state management in React
React Query for Firestore, that you can actually use in production, on every screen.
A collection of tools for neural compression enthusiasts.
Massively parallel rigidbody physics simulation on accelerator hardware.
General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for…
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
Visualize tensors in a plain Python REPL using Sparklines
🤖 Powerful asynchronous state management, server-state utilities and data fetching for the web. TS/JS, React Query, Solid Query, Svelte Query and Vue Query.
A boilerplate for building scalable, maintainable and performant web applications 💥
🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax
Pytorch implementation of High-Fidelity Generative Image Compression + Routines for neural image compression
Sum product algorithm - Belief propagation (message passing) for factor graphs
This repository contains implementations and illustrative code to accompany DeepMind publications
Sum Product Flow: An Easy and Extensible Library for Sum-Product Networks