nanogpt
from Orchestra-Research/AI-research-SKILLs
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 fro
v1.0.0MIT
291
Lines
910
Words
18
Code Blocks
Languages
bashpython
01-model-architecture/nanogpt/SKILL.md