home/categories/machine-learning/scientiacapital-unsloth-mcp-server-claude-skills-superbpe-skill-md
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.

ScientiaCapital
maintainer
ScientiaCapital
更新于 1/18/2026
星标
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.

安装
$ install --globalskills.sh
使用

安装后,您可以通过在终端运行以下命令来使用此技能:

skills use superbpe