tom-doerr

grok-1

Grok open release

AnimateDiff

Official implementation of AnimateDiff.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

EMO

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

ALVR

Stream VR games from your PC to your headset via Wi-Fi

nvitop

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

grok

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

httrack

HTTrack Website Copier, copy websites to your computer (Official repository)

clarity-upscaler

Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

i3blocks

The hacker-friendly status_command for Sway and i3

container2wasm

Container to WASM converter

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

stable-audio-tools

Generative models for conditional audio generation

fsdp_qlora

Training LLMs with QLoRA + FSDP

dstack

An open-source container orchestration engine for running AI workloads in any cloud or data center. https://discord.gg/u8SmfwPpMd

MotionCtrl

MotionCtrl: A Unified and Flexible Motion Controller for Video Generation

pgmock

In-memory Postgres for unit/E2E tests

AQLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

flashinfer

FlashInfer: Kernel Library for LLM Serving

distrifuser

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

piecewise-rectified-flow

prismatic-vlms

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

stable-diffusion-benchmarks

Comparison of different stable diffusion implementations and optimizations

v-rag

Visual RAG using less than 300 lines of code.

onefiveeight

zsh_sodex

An ENHANCED version of a zsh_codex plugin with Guidance and some black-magic.