Making large AI models cheaper, faster and more accessible

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

The official implementation of Self-Play Preference Optimization (SPPO)

Code for explaining and evaluating late chunking (chunked pooling)

AgentScope: Agent-Oriented Programming for Building LLM Applications

SGLang is a fast serving framework for large language models and vision language models.

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

A generative speech model for daily dialogue.

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

AUTOMATIC1111 (A1111) Stable Diffusion Web UI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

🎛 A Svelte library for building dynamic, infinitely customizable node-based user interfaces and flowcharts

StackExchange websites to ZIM scraper

Declarative web scraping

📊 Cube Core is open-source semantic layer and LookML alternative for AI, BI and embedded analytics

The full WorldWide Telescope rendering engine in JavaScript with WebGL

Implementation of disco-diffusion wrapper that could run on your own GPU with batch text input.

A GitHub Actions automated CentOS RootFS to use with WSL

Compiler and runtime engine for NetLogo models that runs in JavaScript 🐢

NetLogo model simulation visualizer (Beak) and the netlogoweb.org website 🐢

💫 Industrial-strength Natural Language Processing (NLP) in Python

🪐 End-to-end NLP workflows from prototype to production

Simulating Knowledge Dynamics in Innovation Networks

A set of scripts to grab public datasets from resources related to arXiv

Command line OAI-PMH harvester and client with built-in cache.

💄 A gorgeous responsive theme for Hexo blog framework

PyTorch Library for Low-Latency, High-Throughput Graph Learning on GPUs.

Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes.