gpt-2-3-tokenizer

所属分类:GPT/ChatGPT
开发工具:JavaScript
文件大小:544KB
下载次数:0
上传日期:2023-03-29 15:45:54
上 传 者sh-1993
说明:  GPT-2 3令牌化器基于@latitudegames GPT-3编码器,可在浏览器和Deno中工作
(GPT-2/3 tokenizer based on @latitudegames/GPT-3-Encoder that works in the browser and Deno ,)

文件列表:
encoder.js (1042317, 2023-03-29)
mod.js (3755, 2023-03-29)
vocab.bpe.js (478414, 2023-03-29)

# GPT-2/3 Tokenizer GPT-2/3 byte pair encoder/decoder/tokenizer based on [@latitudegames/GPT-3-Encoder](https://github.com/latitudegames/GPT-3-Encoder) that works in the browser and Deno. See also: [JS byte pair encoder for OpenAI's CLIP model](https://github.com/josephrocca/clip-bpe-js). ```js 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, 187***, 995] console.log(decode(encode(text))); // "hello world" ``` or: ```js let mod = await import("https://deno.land/x/gpt_2_3_tokenizer@v0.0.2/mod.js"); mod.encode("hello world"); // [258, 187***, 995] ``` or to include it as a global variable (as if you were importing it with the old script tag style): ```html ``` # License The [original code is MIT Licensed](https://github.com/latitudegames/GPT-3-Encoder/blob/master/LICENSE) and so are any changes made by this repo.

近期下载者

相关文件


收藏者