Simple RL training for reasoning

A light weight library that extends instrictor lib for llm based task

The Abstraction and Reasoning Corpus

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Python implementation of CMA-ES

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Deep Learning for humans

A recurrent neural network heavily inspired by Long Short Term Memory, but simpler.

An implementation of Long Short Term Memory in Java.

An implementation of a generalized version of the Long Short-Term Memory neural network architecture and algorithm, one of the most powerful supervised machine learning methodologies

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…