Joshua Lochner

> Love the package, and am using it in research Hey there! That's awesome! 🤗 Please share it when you're done, I would love to see! > I am wondering,...

Here's the rust code for it: https://github.com/huggingface/tokenizers/blob/25aee8b88c8de3c5a52e2f9cb6281d6df00ad516/tokenizers/src/processors/sequence.rs#L18-L36 and it should be easy to translate into JS.

I added support for it in #771. See [here](https://github.com/xenova/transformers.js/pull/771#issue-2311740039) for example usage.

Hi there 👋 Indeed, this is on our list :) The main issue is that the WebGPU version is still pretty slow, but now that we have Phi-3 running w/...

It's out! https://huggingface.co/spaces/Xenova/experimental-moondream-webgpu https://github.com/xenova/transformers.js/assets/26504141/18c37e8b-ffa3-4cba-a824-201bfe53673a See the [model card](https://huggingface.co/Xenova/moondream2) for usage instructions.

Will most likely do one tomorrow. Just finalizing a few other things. :)

Thanks for the report. We haven't yet got encoder-decoder models working with v3, so this error is expected (at least for now). I will close this issue once we do...

I agree! :) Perhaps a community member is interested in creating one?

Hi there 👋 This functionality is not yet added to Transformers.js, but I think it will be great to add! Do you have any specific example code, which will help...

@0xWOLAND We are actively working on this, but for the most part, it will depend on the release of onnxruntime v1.17.3, which fixes several issues with these models. @calumk Are...