🤗 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.

A feature-rich command-line audio/video downloader

Animation engine for explanatory math videos

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

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

The best ChatGPT that $100 can buy.

You like pytorch? You like micrograd? You love tinygrad! ❤️

Data validation using Python type hints

The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Toolkit for linearizing PDFs for LLM datasets/training

An extremely fast Python type checker and language server, written in Rust.

Machine learning, in numpy

Machine Learning Engineering Open Book

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

100 numpy exercises (with solutions)

A hyperparameter optimization framework

An open source implementation of CLIP.

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Declarative visualization library for Python

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

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

the portable Python dataframe library

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams