An app that brings language models directly to your phone.

🚀 Simple share intent in an Expo Native Module

A TTS model capable of generating ultra-realistic dialogue in one pass.

qwen running locally in your browser

Mixins for Tailwind CSS provides a declarative API for creating reusable groups of utilities, reducing code duplication and improving maintainability while emphasizing a utility-first approach.

XState helper for using asynchronous guards.

Use Mongodb queries in JavaScript

Our current standard for podcast RSS feeds.

React Native Expo Share Intent Demonstration

A multilingual text-to-speech synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek.

🦹‍♂️ Twin blends the magic of Tailwind with the flexibility of css-in-js (emotion, styled-components, solid-styled-components, stitches and goober) at build time.

Browser Extension Template with ESbuild builds, support for React, Preact, Typescript, Tailwind, Manifest V3/V2 support and multi browser build including Chrome, Firefox, Safari, Edge, Brave.

WavJourney: Compositional Audio Creation with LLMs

Focus on prompting and generating

A local-first and universal knowledge graph, personal search engine, and workspace for your life.

AI chat for any model.

Export Hugging Face models to Core ML and TensorFlow Lite

Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models

Fast inference engine for Transformer models

🔊 Text-Prompted Generative Audio Model

Source code for the X Recommendation Algorithm

Tensor library for machine learning

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Robust Speech Recognition via Large-Scale Weak Supervision

Code and documentation to train Stanford's Alpaca models, and generate the data.