Apple's new LLM has arrived. The name's - Ferret.

Ferret is a Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions.

Read the paper here:
https://arxiv.org/abs/2310.07704

Github repo:
https://github.com/apple/ml-ferret

#LLM

🆔 @GITAnet|باشگاه فناوران اطلاعات مکانی