SillyTavern/public/scripts/gpt-2-3-tokenizer
Cohee edd41989fd Initial commit 2023-07-20 20:32:15 +03:00
..
README.md Initial commit 2023-07-20 20:32:15 +03:00
encoder.js Initial commit 2023-07-20 20:32:15 +03:00
mod.js Initial commit 2023-07-20 20:32:15 +03:00
vocab.bpe.js Initial commit 2023-07-20 20:32:15 +03:00

README.md

GPT-2/3 Tokenizer

GPT-2/3 byte pair encoder/decoder/tokenizer based on @latitudegames/GPT-3-Encoder that works in the browser and Deno.

See also: JS byte pair encoder for OpenAI's CLIP model.

import {encode, decode} from "https://deno.land/x/gpt_2_3_tokenizer@v0.0.2/mod.js";
let text = "hello world";
console.log(encode(text)); // [258, 18798, 995]
console.log(decode(encode(text))); // "hello world"

or:

let mod = await import("https://deno.land/x/gpt_2_3_tokenizer@v0.0.2/mod.js");
mod.encode("hello world"); // [258, 18798, 995]

or to include it as a global variable in the browser:

<script type=module>
  import tokenizer from "https://deno.land/x/gpt_2_3_tokenizer@v0.0.2/mod.js";
  window.tokenizer = tokenizer;
</script>

License

The original code is MIT Licensed and so are any changes made by this repo.