Jee Jee Li

Hi， Is your issue solved? using the caffe model of this repository, I can't get the correct output value([-1,1]) ,such as 10.111，-9.433

@szagoruyko thanks for your help, so how do i evaluate similarity of images use the output？thank you very much

@liulei01 your dataset is so big for me, can you upload smaller dataset( eg. about 2G ),I just want to learn the process of training with your dataset thank you...

@liulei01 thanks for your answer， it is difficult for me to download your data, but now I have downloaded your dataset using VIP ,hhh~

当然可以了,而且这个Attention应该是借鉴SENet

refer to:https://github.com/vllm-project/vllm/issues/3543

@hipudding Great work. I have a server with 8 *910b, can I test this PR on the 910b?

> > @hipudding Great work. > > I have a server with 8 *910b, can I test this PR on the 910b? > > Yes, you can test operators on...

> Will larger vocabulary size for multi-lora be supported in Q2 2024? Related: #3000 https://github.com/vllm-project/vllm/pull/4015 had done this

> > > Will larger vocabulary size for multi-lora be supported in Q2 2024? Related: #3000 > > > > > > #4015 had done this > > This is...