A single-header, zero-dependency BPE tokenizer for LLMs in C++17 — byte-exact with OpenAI's tiktoken (cl100k, o200k). Count GPT-4/GPT-4o tokens natively
-
Updated
Jul 15, 2026 - C++
8000
A single-header, zero-dependency BPE tokenizer for LLMs in C++17 — byte-exact with OpenAI's tiktoken (cl100k, o200k). Count GPT-4/GPT-4o tokens natively
Add a description, image, and links to the token-counting topic page so that developers can more easily learn about it.
To associate your repository with the token-counting topic, visit your repo's landing page and select "manage topics."