jamesthesnake

croissant

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

fMRI-foundation-model

Self-supervised fMRI foundation model

imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

JAX-Toolbox

JAX-Toolbox

N64-RPG

An RPG engine made for the Nintendo 64

pytorch_geometric

Graph Neural Network Library for PyTorch

sample-app

Sample app for the Radio SDK

slamplay

slamplay is a collection of powerful tools to start playing and experimenting with SLAM in C++

SparesMOE

ra

streaming-llm

Efficient Streaming Language Models with Attention Sinks

vimGPT

Browse the web with GPT-4V and Vimium

Zelda-remake

ColossalAI

Colossal-AI: A Unified Deep Learning System for Big Model Era

columnformers

A Transformer-inspired model of the brain

diffseg

DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements the main DiffSeg algorithm and additionally includes an experimental feature to add semantic labels to the masks based on a generated caption.

facefusion

Next generation face swapper and enhancer

fine-tune-llma

finetune

gpt-pilot

Dev tool that writes scalable apps from scratch while the developer oversees the implementation

JailbreakingLLMs

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

mamba-chat

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

MidiTok

MIDI / symbolic music tokenizers for Deep Learning models 🎶

nebula

Nebula is an open-source and free-to-use modern C++ game engine.

octo

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

PiPPy

Pipeline Parallelism for PyTorch

protein-lm-scaling

pyscf

Python module for quantum chemistry

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Tensors.jl

Efficient computations with symmetric and non-symmetric tensors with support for automatic differentiation.

WebcamGPT-Vision

Lightweight GPT-4 Vision processing over the Webcam