DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Repository Index
142,273 visible repositories in the index
3,025–3,048 of 10,969 · Most stars
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
- ai-agent-tools
- context-compression
- context-pruning
- context-window-optimization
Easy token price estimates for 400+ LLMs. TokenOps.
This project aims to compare and evaluate the telemetry of various EDR products.
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
- music-transcription
- drum-transcription
- vocal
- beat-tracking
Personalized, user-focused recommendations for employee information security.
[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs
A full spaCy pipeline and models for scientific/biomedical documents.
- scientific-documents
- spacy
- custom-pipes
- nlp
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
- vae
- benchmarking
- beta-vae
- comparison
Enable Gemini in Chrome, AI Powered History search, DevTools Al Innovations in Google Chrome without cleaning data and reinstall.
- ai
- ai-browser
- ai-browser-automation
- ai-browser-control
Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.
- lstm
- rnn-tensorflow
- stock-price-prediction
- embeddings
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
A machine learning toolkit for log parsing [ICSE'19, DSN'16]
- log
- log-mining
- log-analysis
- log-parser
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
- pytorch
- knowledge-distillation
- deep-neural-networks
- cifar10
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
- agent-skills
- agentic-ai
- cli-tool
- domain-adaptation
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
- deep-learning
- machine-learning
- time-series
- time-series-forecasting
CVNets: A library for training computer vision networks
- ade20k
- classification
- computer-vision
- deep-learning
The official FlexGet repository
- python
- automation
- torrent
- movies
Worldwide building footprints derived from satellite imagery
Open World Holidays Framework
- python
- holiday
- calendar
- holiday-api
GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]
- face-manipulation
- facial-expressions
- deep-learning
- generative-adversarial-network
pip script installer
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
- artificial-intelligence
- attention-mechanisms
- deep-learning
- text-to-video
[RSS 2026] Causal video-action world model for generalist robot control