An open-source ChatGPT app with a voice

The simplest way to run LLaMA on your local machine

Port of Facebook's LLaMA model in C/C++

VisualChatGPT

Upload a photo of your room to generate your dream room with AI.

A number of experiments using GPT-3, delivered in a web app

Let us control diffusion models!

Transfer the ControlNet with any basemodel in diffusers🔥

Train to 94% on CIFAR-10 in less than 7 seconds on a single A100, the current world record. Or ~95.80% in ~120 seconds (or less!).

Reverse engineered API of Microsoft's Bing Chat

An example project demonstrating the Puter.js SDK

Running large language models like ChatGPT/GPT-3/OPT-175B on a single GPU. Up to 100x faster than other offloading systems.

🎓 Path to a free self-taught education in Computer Science!

This repository contains demos I made with the Transformers library by HuggingFace.

ChatRWKV is like ChatGPT but powered by the RWKV (100% RNN) language model, and open source.

Dynamically generated social images from Svelte components

Port of OpenAI's Whisper model in C/C++

Secure and fast microVMs for serverless computing.

A curated list with resources about node-based UIs

Hybrid visual and textual functional programming.

Stable Diffusion inference on iOS / macOS using MPSGraph

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Latent Text-to-Image Diffusion

🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.

Text generator is a handy plugin for Obsidian that helps you generate text content using GPT-3 (OpenAI).

This version of Stable Diffusion features a slick WebGUI, an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, and multiple features…