Apple Ferret, a Multimodal LLM capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions. I hope this will use Apple MLX for training soon 🚀 https://t.co/RM8z5AK0Lk https://t.co/a5R32YlK4d
— ifioravanti (@ivanfioravanti) Jan 21, 2024
from Twitter https://twitter.com/ivanfioravanti
January 21, 2024 at 08:02PM
via IFTTT
No comments:
Post a Comment