Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)

Copyright (c) 2026 Mithil Maske

This package and its associated model weights are licensed under the Creative
Commons Attribution-NonCommercial 4.0 International License.

You are free to:

  Share  - copy and redistribute the material in any medium or format
  Adapt  - remix, transform, and build upon the material

Under the following terms:

  Attribution  - You must give appropriate credit, provide a link to the
                 license, and indicate if changes were made.

  NonCommercial - You may not use the material for commercial purposes.

Full license text: https://creativecommons.org/licenses/by-nc/4.0/legalcode


WHY NON-COMMERCIAL
------------------

QuadEmbed is built on top of three frozen pretrained encoders. One of them,
jinaai/jina-embeddings-v5-text-nano, is itself licensed CC BY-NC 4.0, and it
defines the embedding space that the trained projectors map into. That
non-commercial restriction therefore carries through to this work.

The other two frozen encoders are permissively licensed:
  - google/siglip2-base-patch16-naflex  (Apache-2.0)
  - openai/whisper-large-v3             (Apache-2.0)

If you need commercial use, you would need a separate license for the text
encoder from Jina AI, or to retrain the projectors against a permissively
licensed text encoder instead.


ATTRIBUTION
-----------

The architecture reproduced here (GELATO) is described in Jina AI's paper on
jina-embeddings-v5-omni, arXiv:2605.08384. This project is an independent
reproduction and is not affiliated with or endorsed by Jina AI.
