Tokenization & Preprocessing
belladoreai/llama3-tokenizer-js
JS tokenizer for LLaMA 3 and LLaMA 3.1
JavaScriptMITupdated Jul 28, 2025
JS tokenizer for LLaMA 1 and 2
$ git clone https://github.com/belladoreai/llama-tokenizer-js.gitJS tokenizer for LLaMA 3 and LLaMA 3.1
Language model tokenization at GB/s
Parser Building Toolkit for JavaScript
Optimised tokenizer/lexer generator! ๐ Uses /y for performance. Moo.
:herb: NodeJS PHP Parser - extract AST or tokens
Data from GitHub ยท snapshot Sep 24, 2026