Efficient World Models with Context-Aware Tokenization. ICML 2024

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

MoMo: Momentum Models for Adaptive Learning Rates

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Flood-Filling Networks for instance segmentation in 3d volumes.

Deep learning at the speed of light.

Implementation of Key-Locked Rank One Editing, from Nvidia AI

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

Implementation of Diffusion Policy, Toyota Research's supposed breakthrough in leveraging DDPMs for learning policies for real-world Robotics

Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!

Dark Mode PDF Reader built using Electron and PDF.js

Implementation of Dreamer v3 in pytorch.

RL research on Android devices.

Test GPT's knowledge of Chess

Physical Symbolic Optimization

Code for Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations

You like pytorch? You like micrograd? You love tinygrad! ❤️