LVM icon indicating copy to clipboard operation
LVM copied to clipboard

About the released weights

Open momo1986 opened this issue 2 years ago • 3 comments

It is a very wonderful project.

Is there a pre-trained model releases that can be utilized in the down-stream vision tasks.

It would be honor that we can do the following work on the basis of the project.

Thanks a lot. Momo

momo1986 avatar Jan 02 '24 07:01 momo1986

There is an alternative code for building LVM: https://github.com/ggjy/DeLVM from our paper: Data-efficient Large Vision Models through Sequential Autoregression

iamhankai avatar Feb 17 '24 02:02 iamhankai

hi, due to some recently raised legal issue of laion: https://laion.ai/notes/laion-maintanence/, we are waiting the filtered version, also working on filtering out the images from our model. thanks for your understanding and patience!

ytongbai avatar Feb 23 '24 07:02 ytongbai

Hi there, are you planning to re-train the model with filtered dataset? Can you release smaller model's weights for us to have fun? It's really frustrating to wait for such a long time... T^T

Spico197 avatar Feb 23 '24 09:02 Spico197