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 tokeniza

by ScientiaCapital· Repository·testing
Run in AgentAreaBrowse All Skills
Also installable via skills CLI
npx skills add ScientiaCapital/unsloth-mcp-server/testing/superbpe

Source

Repo:SkillsMP + GitHub Raw
Path:testing/superbpe(main)

Related in testing

frontend-testing-langgenius-dify

Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files,...

by langgenius
127,079

skill-creator-langgenius-dify

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill)...

by langgenius
127,079

browser-use-browser-use-browser-use

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigat...

by browser-use
76,633