
Rank #747 10,831 starsPython
minbpe
by karpathy (personal account)
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization. (description from the project’s GitHub page)
Repository facts
- Stars
- 10,831
- Forks
- 1,118
- Open issues and pull requests
- 59
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- karpathy · Personal account
- Created
- Feb 16, 2024
- Last push
- Jul 1, 2024