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.

Training a multilingual tokenizer with SentencePiece v1.0.0

Use this resource to train and use a language-independent tokenizer on raw text

New

  • 505 downloads
  • 216 likes
  • 182 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install sentencepiece-tokenizer-training-2

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 guides you through installing SentencePiece, training a BPE or Unigram model on raw text, then encoding and decoding sentences. It suits languages without word separators, such as Chinese, Japanese and Korean.

Mostly picked by

Updated November 2, 2026

Card for the “Training a multilingual tokenizer with SentencePiece” skill

Details

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

Similar resources

View all

What you get

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

Good fit for

  • You build a multilingual model
  • You want reproducible tokenization without preprocessing

Not for

    Tags

    • tokenization
    • multilingual
    • bpe
    • unigram

    About

    You say

    “Train an 8000-entry BPE tokenizer on my Japanese and French corpus.”

    Card for the “Training a multilingual tokenizer with SentencePiece” skill

    Skill published by Orchestra Research 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 language-independent tokenizer on raw text
    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.md5.7 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/02-tokenization/sentencepiece
    Licence
    MIT

    Notice

    « sentencepiece » (Orchestra Research, 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.