Request for Additional Perception Encoder Variants (H and g)

Hello,

The Perception Encoder checkpoints look excellent—thank you for releasing them! However, I noticed that only the ViT-L/G variants are available, and there are no H or g variants. This leaves a gap in intermediate model scales.

Do you have plans to release these additional variants in the future? I am especially looking forward to the PE_lang variant.

Thanks a lot!