Views
No views yet
google/vit-base-patch16-224, tagged for use with
ANEForge so the weights load and run directly on the
Apple Neural Engine (no CoreML). Weights are byte-identical to the source; see the original repo for
the model details. Licensed apache-2.0 from the source.1# pip install "aneforge[models]"
2import aneforge as af
3
4vit = af.load_vit("aneforge/vit-base-patch16-224")
5print(vit.classify(image)) # top-k (label, logit)