Rebuild the Core ML fp16 build with compute_unit=CPU_AND_GPU

Core ML: drop fp32 and make fp16 the default

Add spec-compliant config.json files

Add spec-compliant config.json files

Update models

Update models

Update models. Add quantized models.

Delete coreml/config.json

Upload style_transfer_candy_coreml.pte

Create coreml/config.json