| import json | |
| import sys | |
| from subprocess import getoutput as run_shell | |
| from urllib.request import Request, urlopen | |
| MODEL = "gpt-5.6" | |
| CONTEXT_WINDOW_TOKENS = 1_050_000 | |
| endpoint_url = sys.argv[1] | |
| history = [] |
| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
I’ve written a newer optimized 2026 version of this guide with a faster setup using Zinit + Starship and improved plugin loading.
This version avoids slow shell startups and works better with modern Zsh setups.
Updated guide: https://gist.github.com/n1snt/2cccc8aa5f7b645a7628d3512c70deb6
