From 62da9cec78debb99f969af534b17ad6e0f971349 Mon Sep 17 00:00:00 2001 From: Joshua Lochner Date: Mon, 25 Mar 2024 00:58:36 +0200 Subject: [PATCH] Add warning to `ErnieMTokenizer` class --- src/tokenizers.js | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/src/tokenizers.js b/src/tokenizers.js index b750b04..9b3505b 100644 --- a/src/tokenizers.js +++ b/src/tokenizers.js @@ -4311,7 +4311,12 @@ export class VitsTokenizer extends PreTrainedTokenizer { export class CohereTokenizer extends PreTrainedTokenizer { } -export class ErnieMTokenizer extends PreTrainedTokenizer { } +export class ErnieMTokenizer extends PreTrainedTokenizer { + constructor(tokenizerJSON, tokenizerConfig) { + super(tokenizerJSON, tokenizerConfig); + console.warn('WARNING: `ErnieMTokenizer` is not yet supported by Hugging Face\'s "fast" tokenizers library. Therefore, you may experience slightly inaccurate results.') + } +} /** * Helper class which is used to instantiate pretrained tokenizers with the `from_pretrained` function.