gallerywise/coreml-embeddings
Core ML (.mlpackage, fp16, cpu_and_gpu) conversions of the embedding backbones
used by the on-device pipeline in gallerywise.ai. Converted with
scripts/coreml/convert_embeddings.py
(AIB-72 / AIB-119); loaded at runtime through pyobjc Core ML with no torch in
the shipped app.
Contents
| File | Source model | Notes |
|---|---|---|
siglip_vision.mlpackage.zip |
google/siglip-base-patch16-384 |
vision tower, 768-D |
siglip_text.mlpackage.zip |
google/siglip-base-patch16-384 |
text tower, 768-D |
text_embed.mlpackage.zip |
sentence-transformers/all-MiniLM-L6-v2 |
384-D; mean-pool + L2-normalize baked into the graph (fixed seq-len 64) |
siglip_logit_params.json |
— | SigLIP logit scale/bias |
The .mlpackage bundles are directories, so they are hosted zipped (each
archive contains exactly one top-level *.mlpackage/ entry). The client fetches,
sha256-verifies, and unzips them on first launch.
License & attribution
Apache-2.0, inherited from both source models (SigLIP, all-MiniLM-L6-v2), which are themselves Apache-2.0. These are format conversions (Core ML) of those weights — no retraining or fine-tuning.
Intended use
The gallerywise.ai macOS app's embedding stages (semantic search, zero-shot tags, near-duplicate / moment grouping). Not a general-purpose endpoint.
Model tree for gallerywise/coreml-embeddings
Base model
google/siglip-base-patch16-384
from sentence_transformers import SentenceTransformer model = SentenceTransformer("gallerywise/coreml-embeddings") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3]