Apple’s first public LLM is called Ferret, powered by 8 Nivida A100 GPUs

Apple AI researcher, Zhe Gan, revealed Apple’s Ferret Large Language Model (LLM) in October. (Source: X/Twitter)

Apple is getting serious about generative AI, releasing its first Multimodel Large Language Model dubbed Ferret. The new AI model has been published under an open source license and was trained using 8 Nvidia A100 GPUs.

Apple quietly released its first multimodal Large Language Model (LLM) AI as an open source project, which it has dubbed Ferret. The new Ferret AI was introduced in October by Apple AI researcher Zhe Gan via X/Twitter, but went largely unnoticed until now. Ferret was jointly developed between Gan and his colleagues at Apple, along with researchers at Columbia University. According to Gan, Ferret is more precise at understanding small image regions and describing them than OpenAI’s GPT-4 while producing fewer hallucinations (errors). 

Interestingly, Apple’s Github repository reveals that the company trained Ferret using 8 high-end Nvidia A100 GPUs equipped with 80GB of HBM2e RAM. The A100 is the most in-demand GPU on the market following the explosion of generative AI technology that followed the launch of OpenAI’s ChatGPT late last year. It is capable of 312 TeraFLOPS at Tensor Float 32 precision with the 80GB model used by Apple to train Ferret delivering a bandwidth of up to 2,039 GB/s. The company doesn’t, however, reveal the subject matter it used to train the new model.

While Apple is still in the relatively early stages of its generative AI journey with Ferret, the aim will be to get a model such as Ferret working effectively on a smartphone. OpenAI’s GPT4 is thought to have in excess of 1 trillion parameters, but mobile phones can currently only handle LLMs with around 10 billion parameters. To this end, Apple researchers have also recently made a breakthrough demonstrating how to supplement smartphone RAM with onboard flash storage to shoehorn larger models than might otherwise be possible to run on-device.

A graphic explaining how Ferret works with image recognition. (Source: Apple)

Sanjiv Sathiah – Senior Tech Writer – 1428 articles published on Notebookcheck since 2017

I have been writing about consumer technology over the past ten years, previously with the former MacNN and Electronista, and now Notebookcheck since 2017. My first computer was an Apple ][c and this sparked a passion for Apple, but also technology in general. In the past decade, I’ve become increasingly platform agnostic and love to get my hands on and explore as much technology as I can get my hand on. Whether it is Windows, Mac, iOS, Android, Linux, Nintendo, Xbox, or PlayStation, each has plenty to offer and has given me great joy exploring them all. I was drawn to writing about tech because I love learning about the latest devices and also sharing whatever insights my experience can bring to the site and its readership.

Sanjiv Sathiah, 2023-12-29 (Update: 2023-12-29)

>>> Read full article>>>
Copyright for syndicated content belongs to the linked Source : NotebookCheck – https://www.notebookcheck.net/Apple-s-first-public-LLM-is-called-Ferret-powered-by-8-Nivida-A100-GPUs.787395.0.html