cstr/sface-GGUF

SFace GGUF

GGUF format of SFace (OpenCV Zoo, Apache 2.0) for use with CrispEmbed.

128-dimensional face embedding from MobileFaceNet backbone. Commercially permissive — no non-commercial restrictions.

Parity

Metric	Value
Cosine vs ONNX Runtime	0.999998
Max element diff	0.000224
Architecture	MobileFaceNet (27 conv, PReLU, 128-D)
Input	Aligned 112×112 face crop
BatchNorm	Folded into Conv at conversion time

Quick Start

License

Apache 2.0 (OpenCV Zoo). Commercially permissive — no NC restrictions. Alternative to InsightFace ArcFace (which requires non-commercial license).

Provenance and EU AI Act Art. 53 note

• Upstream model: opencv/face_recognition_sface — published by opencv.
• Upstream licence: apache-2.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
• What was done here: format conversion and/or quantisation only (GGUF/GGML). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
• Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
• Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.