machine-learningdata-ai
superbpe
Train and use SuperBPE tokenizers for 20-33% token reduction across any project. Covers training, optimization, validation, and integration with any LLM framework. Use when you need efficient tokenization, want to reduce API costs, or maximize context windows.
maintainer
ScientiaCapital
更新於 1/18/2026
星標
1
分支
0
quick start
Installation and usage
Train and use SuperBPE tokenizers for 20-33% token reduction across any project. Covers training, optimization, validation, and integration with any LLM framework. Use when you need efficient tokenization, want to reduce API costs, or maximize context windows.
安裝
$ install --globalskills.sh
使用
安裝後，您可以通過在終端運行以下命令來使用此技能：
skills use superbpe