Blake Chi

> Thanks for the final iteration - this looks great so I'm going to merge it now 🔥 ! > > Amazing contribution and thank you for working on it...

Hi @lewtun, Thanks for your reply! `onnx_export` for `SetFitModel` sounds good to me. Sure, happy to lend a hand on adding onnx in this work after #8. :grinning:

Sorry for the waiting time and good new is **Issue #8** has been resolved! Just a suggestion. Maybe @nbertagnolli can work on converting the sklearn head and I can work...

Thanks, @nbertagnolli! Or maybe we can open 2 PR separately? Seems like you are almost ready to open one, so I don't want to hold your back. 😅 But I'm...

okay, sounds good to me :) Make sure you follow @lewtun 's suggestion as below: > Hi @blakechi thanks for your interest in our work! Instead of compiling `SetFitTrainer` into...

Do we also need a Python API for ONNX models? I think it would be much easier for users since we can handle the tokenizer and ONNX runtime for them....

Hi @PhilipMay, I remember @lewtun asked a related problem in [here](https://github.com/huggingface/setfit/pull/149#discussion_r1013770571) in #149. So I think maybe exposed arguments will be preferred in the future. But if we put that...

Hello @younesbelkada, I would like to take [DetrLayer](https://github.com/huggingface/transformers/blob/95754b47a6d4fbdad3440a45762531e8c471c528/src/transformers/models/detr/modeling_detr.py#L610). Nice tutorial btw 😀

Hi @PhilipMay, Sorry for the late reply. That's an interesting idea! I tried adding a dropout layer, and unfortunately, I saw the performance dropped significantly with `0.05` dropout rate (I...