Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Core deep-learning frameworks and libraries for pretraining and distributed training.
Signals: deep-learning, neural-network, pytorch, tensorflow, jax, distributed-training, training, deepspeed
2,697 results
Free Book about Deep-Learning approaches for Chess (like AlphaZero, Leela Chess Zero and Stockfish NNUE)
Java Neural Network Framework Neuroph
Bayesian neural network using Pyro and PyTorch on MNIST dataset
Pytorch implementation of the Variational Recurrent Neural Network (VRNN).
Implementing Multiple Layer Neural Network from Scratch
Free hands-on course about Graph Neural Networks using PyTorch Geometric.
This is a configurable Neural Network written in C#. The Network functionality is completely decoupled from the UI and can be ported to any project. You can also export and import fully trained networks and datasets.
This is an efficient implementation of a fully connected neural network in NumPy. The network can be trained by a variety of learning algorithms: backpropagation, resilient backpropagation and scaled conjugate gradient learning. The network has been developed with PYPY in mind.
Building a Bayesian deep learning classifier
Neural networks race (demo)
Learning about and doing projects with recurrent neural networks
No description
HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.
A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL
Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
Drift: DLM Reinforcement Learning Training Framework
PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT
CIKM2023 Best Demo Paper Award. HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
A customisable 2D platform for agent-based AI research
DeepSeek CLI, a command-line AI coding assistant that leverages the powerful DeepSeek Coder models
Minimal library to train LLMs on TPU in JAX with pjit().
Federated Learning for LLMs.
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
24,523 repositories in the index in total.
