Stars
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Making large AI models cheaper, faster and more accessible
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Multiversal tree writing interface for human-AI collaboration
Chess environment for smaller chess variants, AlphaZero-like MCTS-learning, and Concept Detection
irwin - the protector of lichess from all chess players villainous
Didactic chess engine in Python for absolute beginners
Improve your Baduk skills by training with KataGo!
Bit Board Chess (BBC) - The easiest to understand bitboard chess engine by Code Monkey King
Chess reinforcement learning by AlphaGo Zero methods.
Stockfish NNUE (Chess evaluation) trainer in Pytorch
Neural network-based chess engine capable of natural language commentary
A free and strong UCI chess engine
Rust-tokenizer offers high-performance tokenizers for modern language models, including WordPiece, Byte-Pair Encoding (BPE) and Unigram (SentencePiece) models
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
The fastai book, published as Jupyter Notebooks
Funktional generic type-level programming in Rust: HList, Coproduct, Generic, LabelledGeneric, Validated, Monoid and friends.
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
Magic-Sand is a software for operating an augmented reality sandbox
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Simple implementations of forward- and backward-mode automatic differentation in Scala
Quick, graphical, fun introduction to programming in Scala.
Natural language detection library for Rust. Try demo online: https://whatlang.org/