Researchers working for Apple and from Columbia University quietly pushed an open-source multimodal LLM in October, a research release called “Ferret” that can use regions of images for queries.
A ferret in the wild [Pixabay/Michael Sehlmeyer]
A ferret in the wild [Pixabay/Michael Sehlmeyer]
The introduction in October to Github largely flew under the radar, with no announcement or fanfare for its introduction. The code for Ferret was released alongside Ferret-Bench on October 30, with checkpoint releases introduced on December 14.
While it didn’t receive much attention at first, the release became more of a big deal to AI researchers on Saturday, reports VentureBeat. Bart De Witte, operator of an AI-in-medicine non-profit, posted to X about the “missed” release, calling it a “testament to Apple’s commitment to impactful AI research.”
Apple’s ‘Ferret’ is a new open-source machine learning model
Apple’s ‘Ferret’ is a new open-source machine learning model