Youku-mPLUG icon indicating copy to clipboard operation
Youku-mPLUG copied to clipboard

About the pre-trained CLIP model

Open jacqueline-weng opened this issue 1 year ago • 1 comments

The code shows it loads the visual encoder from a CLIP model (clip-vit-b16.pth). I did not find anything mentioned where it comes from. I tried to load clip-vitb16 from OpenAI huggingface, but it has unmatched keys when loading. Is OpenAI's CLIP the required or you have your own trained CLIP?

jacqueline-weng avatar Mar 05 '24 11:03 jacqueline-weng

Hi, do you find the model file?

zhiweibi avatar Jun 07 '24 07:06 zhiweibi