> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kalarislabs.com/llms.txt
> Use this file to discover all available pages before exploring further.

# sentencepiece — AI agent skill for ml training

> Language-independent tokenizer treating text as raw Unicode.

# `sentencepiece`

> Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

**Category:** [ml-training](/research-agent-skills/skills#ml-training) · **License:** MIT · **Version:** 1.0.0

## Install

```bash theme={null}
npx research-agent-skills install sentencepiece
npx skills add KalarisLabs/research-agent-skills --skill sentencepiece
```

## When to use it

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

## Full playbook

Read [SKILL.md](https://github.com/KalarisLabs/research-agent-skills/blob/main/skills/sentencepiece/SKILL.md) for the complete workflow, references and any scripts. The agent installer copies the full skill folder.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.