◀ VibeCruiser

bpe tokenizer trainer

A vibe-coded web demo — play it in your browser, no install. A vibe-coded toy for exploring byte-pair encoding (BPE)

by @rndmcnlly · rndmcnlly/bpe-tokenizer-trainer on GitHubLANG HTMLHOSTED ON RNDMCNLLY.GITHUB.IOUPDATED 26 Aug 2025

Vote and save it — free account with email or sign in with GitHub

Made this, @rndmcnlly? 5+ people played it here → or use email

▶ Play full screen ▲ Vote: free account with email ▲ Or sign in with GitHub

GitHub may ask you to sign in, then to let VibeCruiser “Verify your GitHub identity” and “Act on your behalf”. We only read your profile and email, and never post anything.

Open the live demo Source on GitHub

From the README

A vibe-coded toy for exploring byte-pair encoding (BPE)

Briefly explain BPE (byte pair encoding) and include pseudo code for something that would take in a giant byte array and generate a BPE vocab for it.

BPE is a compression algorithm that iteratively replaces the most frequent pair of adjacent tokens with a new token. Originally designed for text compression, it's now widely used in NLP for tokenization (GPT, BERT, etc.).

The resulting vocabulary contains the original 256 bytes plus learned multi-byte sequences, enabling efficient encoding of common patterns in the data.

Read the full README on GitHub →

Built something like this? Submit your vibe — free account, takes a minute. How listing works.

More like this

Made this?

Claim it: create a free account, then press CLAIM THIS in the cruiser. Put the badge below in your README or on your demo page first; that link is how we know it's yours.

Your project is on the cruise, loaded live from your own site. Put the badge in your README or on the demo page: it shows your live play count, it links back to this page, and everyone who lands here is one click from running the real thing.

On VibeCruiser

How listing, the badge and claiming work →