Instant-loading web apps, without effort

An open-source & self-hostable Heroku / Netlify / Vercel alternative.

Postgres.js - The Fastest full featured PostgreSQL client for Node.js, Deno, Bun and CloudFlare

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

Zero-Shot Speech Editing and Text-to-Speech in the Wild

The official TypeScript/JS client library and query builder for EdgeDB

ULID generator for NodeJS and the browser

Godot 4 demo with a plug-and-play 3D Third-Person Shooter (TPS) character controller inspired by games like Ratchet and Clank.

The Unofficial Cross-Platform UE4 Launcher

Extensions and utilities for GMCv2 beyond the scope of Grim's actual plugin.

A little motion trajectory component atop GMCv2, carved out of my own project for other GMCv2 licensees who might find it useful.

Distance matching plugin

Unreal Engine plugin that automatically sets up character footsteps without any code.

Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one

A backport of the Realtek Wifi 5 drivers from the wireless-next repo.

Stable Diffusion in pure C/C++

LlamaIndex is a data framework for your LLM applications

Generative Models by Stability AI

Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates

Inference Llama 2 in one file of pure C

mPLUG-Owl & mPLUG-Owl2: Modularized Multimodal Large Language Model

SkyPilot: Run LLMs, AI, and Batch jobs on any cloud. Get maximum savings, highest GPU availability, and managed execution—all with a simple interface.

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning library

QLoRA: Efficient Finetuning of Quantized LLMs

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

Reverse Instructions to generate instruction tuning data with corpus examples

Node.js implementation binding for the RWKV.cpp module

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

Script and instruction how to fine-tune large RWKV model on your data for Alpaca dataset