Learning to Compose Domain-Specific Transformations for Data Augmentation

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

Train transformer language models with reinforcement learning.

Fast, memory-efficient, scalable optimization of deep learning with differential privacy

Python packaging and dependency management made easy

Illustrating estimation of model evidences by nonequilibrium MCMC

Examples of AI Accelerators - GPU, AWS Inferential and Elastic Inference

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

Release for Improved Denoising Diffusion Probabilistic Models

Diffusion-LM

Example notebooks that show how to apply quantum computing with Amazon Braket.

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

Notebooks and examples on how to onboard and use various features of Amazon Personalize

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

dpart: General, flexible, and scalable framework for differentially private synthetic data generation, developed by hazy.

An implementation of the tools described in the paper entitled "Graphical-model based estimation and inference for differential privacy"

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

Code for Implicit Generation and Generalization with Energy Based Models

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

Masked Autoregressive Flow

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization