A playbook for systematically maximizing the performance of deep learning models.

Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

TensorFlow code and pre-trained models for BERT

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

Backend that powers the dataset viewer on Hugging Face dataset pages through a public API.

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

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Release for Improved Denoising Diffusion Probabilistic Models

A living collection of deep learning problems

The Prometheus monitoring system and time series database.

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

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

The official Python library for the OpenAI API

Examples and guides for using the OpenAI API

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

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

This repo includes ChatGPT prompt curation to use ChatGPT better.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Neural Networks: Zero to Hero

Experience macOS just like before

Arbitrary kext and process patching on macOS

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

BlackHole is a modern macOS audio loopback driver that allows applications to pass audio to other applications with zero additional latency.

Robust Speech Recognition via Large-Scale Weak Supervision

This is a plugin for https://github.com/logseq/logseq to provide mindmap support based on https://github.com/markmap/markmap.

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.