Chris Ha's Projects
aHash is a non-cryptographic hashing algorithm that uses the AES hardware instruction
Antialiasing cnns to improve stability and accuracy. In ICML 2019.
Official implementation of "Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network"
An awesome list of data deduplication use cases, papers, tools, and methods.
Official repository for Big-Little Net
Minimalist ML framework for Rust
Truly universal encoding detector in pure Rust - port of Python version
Consistent HashRing
CLRS pseudocode in rust
A PyTorch implementation of CMT based on paper CMT: Convolutional Neural Networks Meet Vision Transformers.
Simple object to count Rust iterables
Project portfolios as part of final and assignment projects from Colorado University MSCS classes
Blazing fast concurrent HashMap for Rust.
Tools for managing datasets for governance and training.
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble
Data and tools for generating and inspecting OLMo pre-training data.
Data processing system for polyglot
Work-in-progress educational programming game
Bindings to copy of SentencePiece esaxx library (fast suffix array and frequent substrings).
Faster concurrent atomic number updates
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Native Rust port of Google's HighwayHash, which makes use of SIMD instructions for a fast and strong hash function
Pretty basic theme for Hugo that covers all of the essentials. All you have to do is start typing!
Extra iterator adaptors, iterator methods, free functions, and macros.
Open Source Differentiable Computer Vision Library for PyTorch