Mojtaba Valipour
Mojtaba Valipour
Now I'm quite confused with how this repository's files are structured. I thought pretrain.py is the file to pre-train your lightningDOT model. However, it does not appear that the _calc_loss...
Is that the case that pretrain.py is only provided to pre-train the UNITER model? If not then what's the usage of train_itm.py?
I see, thank you. So, essentially your itm implementation is different from the original implementation of itm in UNITER. And yours is based on the CMR in the paper. In...
I understand that there is a PR #516 in progress regarding this support request. However, I was confused if this feature is currently usable or not. I wondered if there...
I just prepared an implementation of DyLoRA on top of PEFT, need further test and some training adjustments. In the meanwhile, let me know what I should consider before making...
> This is amazing. Just started with the original paper, but curious if we can add a non-linear transformation (activation) in-between the two matrix A and B. The proposed method...
When do you think you can add this? and if it's not going to be soon, is there any workaround that I can use this icon for now.
Any update on this?
Thanks for being prompt @Michaelvll. Anything that we can do to help and accelerate this? If you can explain what's the technical barrier and what kind of things need to...
@asaiacai Thank you for your input. Yeah, that can be challenging, will try to ask the AWS team and will let you know if there was any solution for that.