AI & ML interests

None defined yet.

Recent Activity

apple 's collections 15

AIMv2
A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint.
MobileCLIP Models + DataCompDR Data
MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models.
AIMv2
A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint.
MobileCLIP Models + DataCompDR Data
MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models.