Implementation of the new SOTA for model based RL, from the paper "Improving Transformer World Models for Data-Efficient RL", in Pytorch

Model-based reinforcement learning in TensorFlow

Reinforcement learning done inside of learned world models

Transformer-based World Models

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

Implementation of Decoder only Transformers for experimentation

LPIPS metric. pip install lpips

Vector (and Scalar) Quantization, in Pytorch

This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf

Implementation of variational auto-encoders trained using an adversarial perceptual loss

A playbook for systematically maximizing the performance of deep learning models.

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)

VAEGAN from "Autoencoding beyond pixels using a learned similarity metric" implemented in Pytorch. Clean, clear and with comments.

PyTorch implementation of VAEGAN

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

A python library for self-supervised learning on images.

Goven (go-oven) is a go library that allows you to have a drop-in query language for your database schema.

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

A skilled virtual assistant for Obsidian.

A template for creating a well behaved system service for your Python program.

Toy example of an applied ML pipeline for me to experiment with MLOps tools.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Models and examples built with TensorFlow

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

📝 Algorithms and data structures implemented in JavaScript with explanations and links to further readings

A list of SaaS, PaaS and IaaS offerings that have free tiers of interest to devops and infradev