llama3 implementation one matrix multiplication at a time

Deep Reinforcement Learning: Zero to Hero!

A tiny lib with pocket-sized implementations of machine learning models in NumPy, most of which will fit in a tweet.

LLM training in simple, raw C/CUDA

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Fast approximate nearest neighbor searching in Rust, based on HNSW index

MULTR is a new Unbiased Learning to Rank method. It leverages the pseudo clicks from user simulator and combines with real clicks in a doubly robustness way, which obtains a low bias and low varian…

allRank is a framework for training learning-to-rank neural models based on PyTorch.

</> htmx - high power tools for HTML

functional programming library for golang

Deep learning in Rust, with shape checked tensors and neural networks

Minimalist ML framework for Rust

Inference Llama 2 in one file of pure C

Inference Llama 2 in one file of pure C

A lightning-fast search API that fits effortlessly into your apps, websites, and workflow

Fullstack app framework for web, desktop, mobile, and more.

A modern Python package and dependency manager supporting the latest PEP standards

Port of OpenAI's Whisper model in C/C++

LLM inference in C/C++

DMG-01 Emulator in Rust

background rust code check

minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.

Go AI program which implements the AlphaGo Zero paper

A "build to learn" Alpha Zero implementation using Gradient Boosted Decision Trees (LightGBM)

Monte Carlo tree search in JAX

AlphaZero in JAX

Cross platform rendering in Rust