bhchiang

readability

Readability is a library written in Go (golang) to parse, analyze and convert HTML pages into readable content. Originally an Arc90 Experiment, it is now incorporated into Safari’s Reader View.

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

tamagui

Style React fast with 100% parity on React Native, an optional UI kit, and optimizing compiler.

tortoise-tts

A multi-voice TTS system trained with an emphasis on quality

accelerate

🚀 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

WebShop

[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

LMOps

General technology for enabling AI capabilities w/ LLMs and MLLMs

platform

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

aioweb3

barracuda-release

ADOP

magenta

Magenta: Music and Art Generation with Machine Intelligence

symbolic-music-diffusion

Symbolic Music Generation with Diffusion Models

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

blue-space

jaxline

jax_dataclasses

Pytrees + dataclasses ❤️

loconotion

📄 Python tool to turn Notion.so pages into lightweight, customizable static websites

pixloc

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)

AtLoc

AtLoc: Attention Guided Camera Localization

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

jaxopt

Hardware accelerated, batchable and differentiable optimizers in JAX.

simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

stats205_notes

the public repo for stats205 scribe notes at Stanford University

detr

End-to-End Object Detection with Transformers

ml-hypersim

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

TurboTransformers

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

TLIO

Tight Learned Inertial Odometry

functorch

functorch is JAX-like composable function transforms for PyTorch.