Created
November 27, 2023 13:46
-
-
Save Mearman/85080f34fe75194c664b3d185f462f0e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import claude from "@anthropic-ai/tokenizer/claude.json"; | |
import { Tiktoken, TiktokenBPE } from "js-tiktoken"; | |
export function countTokens(text: string): number { | |
const tokenizer = getTokenizer(); | |
const encoded = tokenizer.encode(text.normalize("NFKC")); | |
return encoded.length; | |
} | |
export function getTokenizer(): Tiktoken { | |
const tiktokenBPE: TiktokenBPE = { | |
pat_str: claude.pat_str, | |
special_tokens: claude.special_tokens, | |
bpe_ranks: claude.bpe_ranks, | |
}; | |
return new Tiktoken(tiktokenBPE); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment