Meta unveils a brand new massive language mannequin that may run on a single GPU [Updated]

A dramatic, colorful illustration.

Enlarge (credit score: Benj Edwards / Ars Technica)

On Friday, Meta introduced a brand new AI-powered massive language mannequin (LLM) known as LLaMA-13B that it claims can outperform OpenAI’s GPT-Three mannequin regardless of being “10x smaller.” Smaller-sized AI fashions may result in working ChatGPT-style language assistants domestically on units comparable to PCs and smartphones. It is a part of a brand new household of language fashions known as “Giant Language Mannequin Meta AI,” or LLAMA for brief.

The LLaMA assortment of language fashions vary from 7 billion to 65 billion parameters in dimension. By comparability, OpenAI’s GPT-Three mannequin—the foundational mannequin behind ChatGPT—has 175 billion parameters.

Meta educated its LLaMA fashions utilizing publicly out there datasets, comparable to Frequent Crawl, Wikipedia, and C4, which implies the agency can probably launch the mannequin and the weights open supply. That is a dramatic new improvement in an business the place, up till now, the Huge Tech gamers within the AI race have saved their strongest AI know-how to themselves.

Learn 7 remaining paragraphs | Feedback

Leave a Reply

Your email address will not be published. Required fields are marked *