text-davinci-003 Tokenizer
A π€-compatible version of the text-davinci-003 tokenizer (adapted from openai/tiktoken). This means it can be used with Hugging Face libraries including Transformers, Tokenizers, and Transformers.js.
Example usage:
Transformers/Tokenizers
from transformers import GPT2TokenizerFast
tokenizer = GPT2TokenizerFast.from_pretrained('Xenova/text-davinci-003')
assert tokenizer.encode('hello world') == [31373, 995]
Transformers.js
import { AutoTokenizer } from '@xenova/transformers';
const tokenizer = await AutoTokenizer.from_pretrained('Xenova/text-davinci-003');
const tokens = tokenizer.encode('hello world'); // [31373, 995]