NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Provides end-to-end model development pipelines for LLMs and Multimodal models that can be launched on-prem or cloud-native.

NYU Deep Learning Spring 2021

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

List of Computer Science courses with video lectures.

NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

Python code for "Probabilistic Machine learning" book by Kevin Murphy

Learning Invariant Representations for Reinforcement Learning without Reconstruction

PFRL: a PyTorch-based deep reinforcement learning library

PyTorch implementation of DARLA preprocessing models

Reinforcement learning with tensorflow 2 keras

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

Pytorch implementation of the Variational Recurrent Neural Network (VRNN).

A Collection of Variational Autoencoders (VAE) in PyTorch.

PRML algorithms implemented in Python

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms