deep-learning

Open-source repository for a NanoGPT training speedrun, focused on getting a 124M model to target loss on 8x H100 GPUs in under 90 seconds. The README includes run commands, Docker instructions, and a detailed list of model and systems optimizations.

A CUDA C++ project for training a tiny byte-level GPT quickly, with build, run, checkpoint, logging, and test instructions in the repo README.

An open-source SDK and CLI for generating human-like mouse movement with deep learning, aimed at developers and agents that need synthetic pointer motion.