EmbeddingGemmaEncoder.mlpackage — CoreML export of EmbeddingGemma 300m (QAT-Q4_0)
Google's EmbeddingGemma 300m (QAT q4_0 weights) exported to a Core ML package producing 768-dimensional sentence embeddings on-device (Apple Neural Engine / GPU / CPU).
Consumed by ES-Memory as its
universal summary embedder, with the model card's prompt conventions:
queries as task: search result | query: …, documents as
title: <title|none> | text: ….
Download
hf download apocryphx/embeddinggemma-300m-qat-q4_0-coreml --local-dir .
Yields EmbeddingGemmaEncoder.mlpackage, loadable with MLModel directly or
compilable to .mlmodelc.
License
Gemma is provided under and subject to the
Gemma Terms of Use. By downloading this
model you agree to those terms, including the
Gemma Prohibited Use Policy.
This repository redistributes a quantized Model Derivative of
google/embeddinggemma-300m; the same terms and use restrictions apply to it
and to any further derivatives.
- Downloads last month
- 8
Model tree for apocryphx/embeddinggemma-300m-qat-q4_0-coreml
Base model
google/embeddinggemma-300m