[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

Fast and memory-efficient exact attention

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

Copilot for your terminal

GMail filtering with regular expressions

A collection of utilities for writing labeling functions, transformation functions, and slicing functions.

Data validation using Python type hints

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Applying Snorkel to SuperGLUE

FastAPI framework, high performance, easy to learn, fast to code, ready for production

MultiMarkdown version of Notational Velocity with Markdown editing features and preview

Multi-user server for Jupyter notebooks

A system for quickly generating training data with weak supervision

Simple framework for creating REST APIs

A collection of tutorials for Snorkel

💫 Industrial-strength Natural Language Processing (NLP) in Python

A deep learning framework for building multimodal multi-task learning systems.

A collection of simple tutorials for using Fonduer

Re-Connectable secure remote shell

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Snorkel MeTaL: A framework for training models with multi-task weak supervision

Knowledge base for YC Applied Machine learning reading group

Efficient video analysis at scale

Lesson content for cryptozombies.io

DAWNBench: An End-to-End Deep Learning Benchmark and Competition

Open3D: A Modern Library for 3D Data Processing