Ofer Idan
Ofer Idan
Hi Man, Thanks for your feedback. Let me clarify my question: I understand the idea of PPL loss, but according to the graph in the paper, it seems that even...
Thanks for the feedback! On Sat, 5 Feb 2022, 07:34 Man M. Ho, ***@***.***> wrote: > Hi Ofer, > > Yes, I noticed that. The ideal result is that the...
that would be great, thanks alot.
hi liupgd, mousecpn , can you please upload your pre-trained model? I understand its not perfect, but it would be great if you can share it. thanks in advanced.
thanks alot, liupgd.
Hi, I am running the pre-trained model and getting same results as acerdur above. did you succeed to fix it? I am using pytorch version 0.4.1. using the original code...
found a fix - after installing pytorch 0.4.1 + torchvision 0.2.2 results are good.
Hi, thanks for getting back to me. Can you please share phi-3 training details with me? For example, lora config , target_modules , etc. I would like to reproduce this...
Thanks alot for your feedback. I think that target_modules "q_proj,k_proj,v_proj" are part of CLIP image encoder in phi-3, while qvk_proj is of LM (in the training script we only train...