MUSE models, but faster and lighter

What about them MUSE models?

Illustration of the alignment process of embedding models (from the MUSE scientific article).

Yes, but can you make them load faster?

  1. download the models
  2. parse them using the original Facebook code
  3. serialize them in a binary format using msgpack
  4. reuse them later
Loading time comparison

Yes, but can you make them lighter?

Model size comparison

Yes, but can you make them available?

--

--

--

AI-powered Order-To-Cash Platform

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Sidetrade Tech Hub

Sidetrade Tech Hub

AI-powered Order-To-Cash Platform

More from Medium

How to Test NLP Models from the Lens of Software Engineering?

Experiences with SOTA Semi-Supervised Learning NLP Algorithms on different public datasets

BERT for Sequence Labelling with Imbalanced Data

If Beam Search is the Answer, What was the Question? — A deep dive