karpathy

karpathy/minbpe

steady

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Python View on GitHub

Stars

10,600

Forks

1,072

Open issues

31

24h

+3

+0.0%

7d

+15

+0.1%

Refresh

2h

Star history (7 days)

Last checked

57m ago

Last pushed

01 Jul 2024

Next check

just now