chrischoy

langchain

🦜🔗 Build context-aware reasoning applications

OpenVoice

Instant voice cloning by MyShell.

Rocket

A web framework for Rust.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

candle

Minimalist ML framework for Rust

mamba

Mamba SSM architecture

bfg-repo-cleaner

Removes large or troublesome blobs like git-filter-branch does, but faster. And written in Scala

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

open_clip

An open source implementation of CLIP.

PhotoMaker

PhotoMaker

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Wonder3D

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

tch-rs

Rust bindings for the C++ api of PyTorch.

lightning-hydra-template

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

langgraph

Build resilient language agents as graphs.

co-tracker

CoTracker is a model for tracking any point (pixel) on a video.

obsidian-copilot

A ChatGPT Copilot in Obsidian

omnimotion

viper

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

SecureAI-Tools

Private and secure AI tools for everyone's productivity.

carefree-drawboard

🎨 Infinite Drawboard in Python

fft-conv-pytorch

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

NVDS

The official repository of the ICCV2023 paper "Neural Video Depth Stabilizer" (NVDS).

BlenderNeuralangelo

Blender addon to inspect and preprocess COLMAP data for Neuralangelo (CVPR 2023)

lab4d

A framework for 4D reconstruction from monocular videos.

nvcc4jupyter

A plugin for Jupyter Notebook to run CUDA C/C++ code

XLB

XLB: Accelerated Lattice Boltzmann (XLB) based on JAX for Physics-based ML

3DVideos2Stereo

Code to extract stereo frame pairs from 3D videos, as used in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, arXiv:1907.01341"