Fix pipeline tag: this is an embedding/retrieval model, not text-to-image generation

Remove duplicated library code; the canonical copy is on PyPI

Point install instructions at the published PyPI package

Link the published Medium write-up

Link the now-live GitHub repo

Rename package gelato_local -> quadembed, drop GELATO from project naming (credit stays in text)

Initial upload: gelato-local-nano (frozen encoders + trained projectors)

initial commit