QNN: LR-ASPP MobileNetV3 a16w8, one context binary per Hexagon version

Remove the Vulkan index-map variant

Add Vulkan fp16 exports

Core ML: emit a (1,520,520) int32 index map instead of (1,21,520,520) logits

Core ML: emit a (1,520,520) int32 index map instead of (1,21,520,520) logits

Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Terminate .gitattributes with a newline

Correct the published metadata

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 coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Add stub root config.json for HF download counter

Add spec-compliant config.json files

Add spec-compliant config.json files

Update models

Add model

Update README

initial commit