⚡ Building applications with LLMs through composability ⚡

This is Octopus open source material

gradslam is an open source differentiable dense SLAM library for PyTorch

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

Python code to fuse multiple RGB-D images into a TSDF voxel volume.

A PyTorch implementation of EventProp [https://arxiv.org/abs/2009.08378], a method to train Spiking Neural Networks

Implementing a small, dense array language using LLVM.

Pytorch implementation of "Group Latent Embedding for Vector Quantized Variational Autoencoder in Non-Parallel Voice Conversion" [Interspeech 2019]

Learning from Synthetic Humans, CVPR 2017

Noise Conditional Score Networks

BibBase Example Page

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains.

A simple commandline utility to generate grid-based signed distance field (level set) generator from triangle meshes, using code from Robert Bridson's website.