Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Remove the superseded legacy MLX build

Update privacy_filter_nemotron_xnnpack_8da4w.pte

feat: dynamic sequence length xnnpack export

Update mlx/config.json

Rename mlx/pf_nemotron_gs64_fp32_seq256.pte to mlx/privacy_filter_nemotron_mlx_int8.pte

Rename mlx/privacy_filter_nemotron_mlx_int8.pte to mlx/privacy_filter_nemotron_mlx_int8_legacy.pte

Upload pf_nemotron_gs64_fp32_seq256.pte

Update mlx/config.json

Rename mlx/privacy_filter_nemotron_mlx_int8_bf16.pte to mlx/privacy_filter_nemotron_mlx_int8.pte

Upload privacy_filter_nemotron_mlx_int8_bf16.pte

Create mlx/config.json

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

Rename xnnpack/privacy_filter_nemotron_single.pte to xnnpack/privacy-filter-nemotron_xnnpack_8da4w.pte

Upload privacy_filter_nemotron_single.pte

Update README.md

Upload 3 files

Create xnnpack/config.json

Update README.md

initial commit