wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk

Fine-tune Stable Audio Open with DiT ControlNet.

real time face swap and one-click video deepfake with only a single image

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Tools for merging pretrained large language models.

Simple Byte pair Encoding mechanism used for tokenization process . written purely in C

Easily train a good VC model with voice data <= 10 mins!

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Python toolkit for quantitative finance

Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers …

LlamaIndex is the leading framework for building LLM-powered agents over your data.

Supercharge Your LLM Application Evaluations 🚀

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

LLM101n: Let's build a Storyteller

The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

Examples and guides for using the Gemini API

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Inference code for CodeLlama models

We write your reusable computer vision tools. 💜

Flower: A Friendly Federated AI Framework

WebUI extension for ControlNet

Let us control diffusion models!

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

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

LangChain for Go, the easiest way to write LLM-based programs in Go

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

starter from "How to Train a GAN?" at NIPS2016

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

This is the Rust course used by the Android team at Google. It provides you the material to quickly teach Rust.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.