Core ML: drop the fp32 variant, fp16 is equivalent in task terms

Remove MLX artifacts: slower than Core ML on device

Add backend config (ExecuTorch 1.4.1)

Add backend config (ExecuTorch 1.4.1)

Add export (ExecuTorch 1.4.1)

Add export (ExecuTorch 1.4.1)

Add export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Update models

fix(v0.9.0): restore 3 backbones (mobilenet_v3_large, resnet50, resnet101) × {fp32,int8} from v0.8.0

Add stub root config.json for HF download counter

Add spec-compliant config.json files

Add spec-compliant config.json files

Restructure to MODEL_SPEC.md convention

Update models

Update models

Update README

Move the model

Upload deeplabV3_xnnpack_fp32.pte

Update README.md

initial commit