Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

SentencePiece: multilingual tokenization v1.0.0

Use this resource to train and use a reproducible multilingual SentencePiece tokenizer

New

  • 546 downloads
  • 235 likes
  • 127 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install sentencepiece-tokenizer-training

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent trains a SentencePiece model with BPE or Unigram on your raw text, from the command line or in Python, then encodes and decodes your sentences. You get a deterministic vocabulary with no language-specific rules.

Mostly picked by

Updated November 2, 2026

Card for the “SentencePiece: multilingual tokenization” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: installation, training and use in Python
  • references/algorithms.md: BPE and Unigram algorithms
  • references/training.md: training parameters

Good fit for

  • You are building a multilingual model or one for Chinese, Japanese or Korean
  • You want reproducible tokenization over large volumes of text

Not for

    Tags

    • tokenization
    • sentencepiece
    • multilingual

    About

    You say

    “Train a BPE SentencePiece tokenizer with an 8,000-token vocabulary on my French and English corpus.”

    Card for the “SentencePiece: multilingual tokenization” skill

    Skill published by davila7 under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to train and use a reproducible multilingual SentencePiece tokenizer
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/algorithms.md4.3 KB
    • references/training.md6.4 KB
    • SKILL.md5.8 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/tokenization-sentencepiece
    Licence
    MIT

    Notice

    « tokenization-sentencepiece » (davila7, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.