A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint.
-
apple/aimv2-large-patch14-224
Image Feature Extraction β’ Updated β’ 3.48k β’ 46 -
apple/aimv2-huge-patch14-224
Image Feature Extraction β’ Updated β’ 116 β’ 9 -
apple/aimv2-1B-patch14-224
Image Feature Extraction β’ Updated β’ 102 β’ 5 -
apple/aimv2-3B-patch14-224
Image Feature Extraction β’ Updated β’ 43 β’ 3