Add Vulkan fp16 exports

Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Put the backend directories back at the repo root

Move the size-n exports under n/ and rewrite the backend configs

NOTES: correct the availability-history claim

Remove MLX artifacts: 7.5-19.6x slower than Core ML on device

Rebuild mlx export with fork toolchain (ExecuTorch 1.4.1)

Rebuild mlx export with fork toolchain (ExecuTorch 1.4.1)

Add coreml fp16 export (ExecuTorch 1.4.1)

Add coreml fp16 export (ExecuTorch 1.4.1)

Remove file uploaded under incorrect path layout

Add export (ExecuTorch 1.4.1)

Add export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Update model

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

chore: update README

Add yolo26-n

initial commit