Karpathy의 microgpt.py 완전 해부: 150줄로 이해하는 GPT의 본질

import os
import math
import random

random.seed(42)

if not os.path.exists('input.txt'):
    import urllib.request
    names_url = 'https://raw.githubusercontent.com/karpathy/makemore/refs/heads/master/names.txt'
    urllib.request.urlretrieve(names_url, 'input.txt')

docs = [l.strip() for l in open('input.txt').read().strip().split('\n') if l.strip()]
random.shuffle(docs)

uchars = sorted(set(''.join(docs)))  # ['a', 'b', ..., 'z'] -> 26글자
BOS = len(uchars)                     # BOS = 26
vocab_size = len(uchars) + 1          # 27