Rebuild the Core ML fp16 build with compute_unit=CPU_AND_GPU

Document why MLX is not shipped: 2.9x slower than Core ML and non-finite output

Core ML: drop fp32 and make fp16 the default

Add stub root config.json for HF download counter

Add spec-compliant config.json files

Add spec-compliant config.json files

Remove old-layout metadata orphaned by MODEL_SPEC.md restructure

Update models

Update models

Update models

Update README

Update models. Add quantized models.

Update .gitattributes

Create LICENSE

Update README.md

Delete xnnpack/config.json

Delete coreml/config.json

Create config.json

Upload style_transfer_rain_princess_xnnpack.pte

Upload style_transfer_rain_princess_coreml.pte

Create xnnpack/config.json

Create coreml/config.json

Update README.md

initial commit