Agent Skills: model-architecture-nanogpt

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

ID: davila7/claude-code-templates/model-architecture-nanogpt

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill model-architecture-nanogpt

Skill Files

The files that make up model-architecture-nanogpt.

Download Skill

More agent skills