Declare the int8 Core ML variant

Add int8 Core ML variant (embedding table quantized)

Core ML: accept a sequence length of 1

Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Add a Vulkan fp16 variant

Core ML: pin compute_unit=CPU_ONLY, drop the fp32 variant

Add per-backend config

Add coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Update .pte files for v0.10.0

Re-export text embeddings with get_dynamic_dims_forward dynamic-shape contract

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

Restructure to MODEL_SPEC.md convention

Upload multi-qa-MiniLM-L6-cos-v1_xnnpack.pte

Upload multi-qa-MiniLM-L6-cos-v1_xnnpack.pte

Upload 2 files (#1)

Change max_length v2

Change max_length

Rename multi-qa-MiniLM-L6-cos-v1.pte to multi-qa-MiniLM-L6-cos-v1_xnnpack.pte

Update README.md

Update config.json

Update config.json

Create config.json

Upload 3 files

initial commit