MobileCLIP-S2 (Core ML)

An unmodified mirror of Apple's MobileCLIP-S2 image and text encoders in Core ML format, from apple/coreml-mobileclip.

  • mobileclip_s2_image.mlpackage: image encoder (256Γ—256 β†’ 512-d embedding)
  • mobileclip_s2_text.mlpackage: text encoder (CLIP tokens β†’ 512-d embedding)

All credit to Apple Machine Learning Research (paper, code). Released under the Apple Machine Learning Research Model License; see LICENSE.

Downloads last month
13
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Paper for grj-models/mobileclip-s2-coreml