Modelpublic

kevinqz/Nomic-Embed-Text-v1.5-CoreAI

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes

Model Card

Canonical: `kevinqz/Nomic-Embed-Text-v1.5-CoreAI` — source of truth.

Nomic Embed Text v1.5 (fabric)

An Apple Core AI conversion of nomic-ai/nomic-embed-text-v1.5 — a text-embedding encoder that maps (input_ids, attention_mask) to a pooled, L2-normalized sentence embedding (cosine-ready). Produced by coreai-fabric and indexed by coreai-catalog.

Encoder, not a chat model. This is a single-forward encoder — token ids in, one 768-d L2-normalized embedding (1×768) out. No text generation, no KV-cache. The host owns the upstream tokenizer and pad/truncate to the static sequence length; compare embeddings with a dot product (cosine).

Model facts

Field	Value
Parameters	0.137B
Architecture	encoder
Capabilities	embedding
Embedding dim	768
Sequence length	128 (static)
Pooling	mean, L2-normalized
Quantization / precision	none / float32
On-disk size	522 MB
Asset kind	single-graph encoder ((inputids, attentionmask) -> unit embedding)
assetVersion	2.0

Use it — this needs host code you supply

The bundle is a single static-sequence graph: (input_ids, attention_mask) [1,128] in → embedding 1×768 out (mean pooling, unit-norm). You supply the upstream tokenizer and pad/truncate in your host code (Swift or Python). Token ids are int32 at the graph boundary.

bash

pip install coreai-catalog && coreai-catalog install nomic-embed-text-v15

Requirements

—Deployment: macOS 27.0+ / iOS 27.0+, Xcode 27+. The asset serializes with minimum_os v27, so the on-device Swift runtime requires macOS/iOS 27+. A Mac on macOS 26 can convert and inspect it but not run it on-device.
—Apple Silicon.

Verification (output parity)

—Gate A (structure): passed — the bundle's layout + metadata were validated; the graph loads.
—Gate B — graph_output_cosine: 1.000000 min output cosine (median 1.000000) vs the fp32 torch sentence encoder over 8 seeded (inputids, attentionmask), measured on apple_silicon. Certifies the export computes the SAME output as the source — a conversion-fidelity metric, not task accuracy.
—This certifies the export is numerically faithful to the source encoder — it does NOT certify retrieval quality on your corpus. Reproduce with coreai-fabric verify.

Provenance

Field	Value
Base model	nomic-ai/nomic-embed-text-v1.5 @ `e9b6763023c676ca8431644204f50c2b100d9aab`
Converted by	`models/embedding/export.py` (version not reported)
Recipe	nomic-embed-text-v15 (recipe_source: fabric)
Precision / quantization	float32 / none
Conversion date	2026-07-10

Machine-readable, in this repo: `parity-report.json` · `reproduce-manifest.json` · `LICENSE`.

License and attribution

Weights licensed apache-2.0 — see the bundled LICENSE. This artifact is a converted derivative of the base model: its weights were converted to Apple Core AI format. The conversion itself is community work.

The on-device Core AI ecosystem

—coreai-fabric — the reproducible recipe → .aimodel pipeline that produced this asset.
—coreai-catalog — the index of Core AI models with provenance and integration snippets.
—apple/coreai-models — Apple's official exporters and runtimes.

Not affiliated with Apple

Community conversion. Not produced, hosted, or endorsed by Apple. Apple and Core AI are trademarks of Apple Inc., used here only to describe the target runtime/format.