Last Friday, Meta Platforms’ co-founder and CEO Mark Zuckerberg announced that the company has trained a new large language model called LLaMA, which will be released to researchers. The model is designed to aid scientists and engineers in exploring AI applications such as answering questions and summarizing documents. Developed by Meta’s Fundamental AI Research (FAIR) team, the release of this new model comes at a time when large tech companies and well-funded startups are competing to showcase advancements in AI techniques and integrate the technology into commercial products.
Applications such as OpenAI’s ChatGPT, Microsoft’s Bing AI, and Google’s Bard rely on large language models. Mark Zuckerberg announced on Friday that Meta’s Fundamental AI Research (FAIR) team has developed a new language model called LLaMA, which could eventually be used to solve math problems or conduct scientific research. According to Zuckerberg, LLMs have shown promise in generating text, summarizing written material, and even solving math theorems or predicting protein structures. One example of LLaMA’s output, from Meta’s paper, is as follows:
Prompt: Here is the recommendation letter that I wrote for an application to a dragon feeder position at the Magic Unicorn Corporation: Dear recruiter,
Response: I have known ___ for two years, and I believe that she would be an excellent dragon feeder for the Magic Unicorn Corporation. ___ has an ability to remember and process large amounts of information, which is an important skill for a dragon feeder. ___, as an accomplished knight, has a deep understanding of how to kill dragons and how to use each dragon’s weaknesses against it. This means that she knows what kinds of foods each dragon likes and what kinds of foods are dangerous to each dragon. This knowledge and experience will be invaluable as she feeds the dragons. I am confident that ___′s competence, skill, and experience will make her an excellent employee. Please contact me at (___) ___-___ if you have any questions. I look forward to hearing from you.
Best regards,
Honorable Knight
Sir George
Here’s the model’s output for a fictional scene from “Seinfeld”:
Prompt: (A hilarious scene between Jerry and George where George presents his new AI watch)
Response: George: “But you see, Jerry, it’s more than just a watch. It’s a minicomputer. You program it any way you want. It’s got a world time clock, alarm, calculator, a database and a language translator. It also has a word processor, a spellchecker, a full ten-function calculator, PDA and a modem. I think it even makes cappuccino.”
Jerry: “Where are you getting this stuff?”
George: “From my ad copy. Look, Jerry, it’s not a watch. It’s an organizer, a personal assistant, and a dictaphone. You can play chess against it. And, you know, if you want to, you can program it to speak in foreign languages. It’s a microprocessor, Jerry.”
Jerry: “George, if you had one of these, would you wear it?”
George: “I’m wearing it right now.”
Jerry: “I don’t see anything on your wrist.”
George: “That’s because it’s a microprocessor.”
Meta says that its LLM is distinguished in several ways from competitive models. First, it says that it will come in several sizes, from 7 billion parameters to 65 billion parameters. Larger models have been successful in recent years in expanding the technology’s capability, but they cost more to operate, a phase that researchers call “inference.” OpenAI’s ChatGPT 3 has 175 billion parameters, for example. Meta also said that it will make its models available to the research public and is taking applications from researchers. The underlying models for Google’s LaMDA and OpenAI’s ChatGPT are not public. “Meta is committed to this open model of research and we’ll make our new model available to the AI research community,” Zuckerberg wrote. Go to Source
Author: Kif Leswing
