Lists (32)
3D Scene Reconstruction
Audio
Audio Generation
Audio synthesisAudio Source Separation
Automatic Speech Recognition
Speech to TextBERT
Bidirectional Encoder Representations from TransformersCapsNet
Capsule Neural NetworksChinese NLP
CLIP
Contrastive Language-Image Pre-trainingComputer Vision
Elixir
Embedding
Erlang
FastText
Word2vec & FastText text embeddingsGraph Neural Networks
GNNImage Classification
Classification of imagesImage Generation
Neural generation of imagesJavaScript
Language Modeling
MIDI
NER
Named Entities RecognitionONNX
Onnx runtime and models weightsProtein Structure Prediction
Python
RL
Reinforcement Learning and AgentsRust
Search
Search EnginesSemantic Search
TensorRT
Text Classification
Wasm
Web AssemblyWord2vec
Stars
A vector index built on TurboQuant, written in Rust with Python bindings
SU-01: Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
DeepSeek 4 Flash local inference engine for Metal and CUDA
TokenSpeed is a speed-of-light LLM inference engine.
Utilities to obtain, generate, and post-process TV listings data in XMLTV format
An open source template for building cloud agents.
An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".
DFlash: Block Diffusion for Flash Speculative Decoding
mac code — Claude Code, but it runs on your Mac for free. 35B AI agent at 30 tok/s via Apple Silicon flash-paging. $0/month.
Hundreds of models & providers. One command to find what runs on your hardware.
Official data.gouv.fr Model Context Protocol (MCP) server that allows AI chatbots to search, explore, and analyze datasets from the French national Open Data platform, directly through conversation.
Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork
Lucebox: LLM inference server built for speed for specific consumer hardware.
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.
`Paper repo for “Coherence-Guided Dead-Head Identification in Frozen Transformers,” including manuscript sources, figures, frozen result artifacts, and verification scripts.`
TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
DGX Spark setup and vLLM deployment scripts for Qwen, GPT-OSS, and Nemotron 3.
Universal Ethernet Direct Connect (UniEDC)
linwumeng / clawd-code
Forked from ultraworkers/claw-codeAn independent Python feature port of alike to Claude Code, entirely rewritting from scratch using oh-my-codex. Educational Purpose only.