Stars
GeNN is a GPU-enhanced Neuronal Network simulation environment based on code generation for Nvidia CUDA and AMD HIP.
Continuous Thought Machines, because thought takes time and reasoning is a process.
Rapid experimentation and scaling of deep learning models on molecular and crystal graphs.
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
A transparent PyTorch micro-framework for pragmatic research code. Comes with a terminal-based IDE for stateful and iterative debugging.
Template machine learning project using wandb, hydra-zen and submitit on Slurm with Apptainer
A very minimal ml project template that uses HF transformers and wandb to train a simple NN and evaluate it, in a stateless manner compatible with Spot instances kubernetes workflows
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.
Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya
Official PyTorch implementation for "Large Language Diffusion Models"
Practice your pandas skills!
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
Official repository for discrete Walk-Jump Sampling (dWJS)
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
A library for mechanistic interpretability of GPT-style language models
Open source replication of Anthropic's Crosscoders for Model Diffing
Training Sparse Autoencoders on Language Models
A scikit-learn compatible neural network library that wraps PyTorch
knakamura13 / mlrose-ky
Forked from hiive/mlroseA highly optimized fork of the popular mlrose-hiive package. For Machine Learning, Randomized Optimization and SEarch algorithms.
Meta-Learning for Compositionality (MLC) for modeling human behavior