I’ve exported a custom PyTorch-based Transformer model into ONNX to run it on NodeJS. However, the exported model seems to expect input_ids directly (and not raw text). Is there any way I can perform tokenization in JS? Or is there something I’m missing, wherein the ONNX model itself is capable of…

I have written a JavaScript library that is capable of running the T5 tokenizer: transformers-js/tokenizers.js at main · praeclarum/transformers-js · GitHub

Awesome library @praeclarum ! I used it as inspiration when developing https://github.com/xenova/transformers.js , which supports BERT, DistilBERT, T5 and GPT2 tokenization and inference.

Thank you, so so much. This library finally made it possible for even a noob such as myself to execute my models in the browser. I’d probably get a C in my Data Mining class if I didn’t find this amazing tool.

Tokenizing using JS

🤗Transformers

praeclarum August 17, 2022, 6:05am 2

I have the same problem. Seems converting to onnx is only half the battle. Maybe I’ll write a library. How hard could it be?

Topic		Replies	Views
How to perform tokenization on an ONNX model in JS? 🤗Tokenizers	0	873	May 6, 2022
How to export bert tokenizer to onnx? 🤗Transformers	0	195	June 25, 2024
Convert bert tokenizer to onnx Beginners	3	3330	November 4, 2022
Exporting tokenizer to an onnx model 🤗Tokenizers	1	1529	June 23, 2024
Convert ASR to ONNX Models	0	943	February 12, 2021

Tokenizing using JS

Related topics