Navigating the World of Large Language Models
bentoml.com
bentoml.com
One thing I didn't mention in this blog post is that developing vertical models tailored to specific industries may be more important than creating general-purpose models.
Actually I have been wondering why we need so many general-purpose models? People in this world come from different industries and what they need is targeted solutions. Vertical models can address nuanced problems that general-purpose models might overlook due to their broad training.
Feel free to leave your comments here :-)
But, I think your HN-comment parent is spot on regarding vertical models vs general purpose.
It would be awesome to see an article about when to try to use general-purpose models vs vertical.
The ability of LLM models to serve as FAQs and chat-bots and everything in-between, is super powerful.
But what are the pros and cons of using vertical vs general purpose LLMs for knowledge bases and chat-bots?
I'd love to see an article that addresses how to create these models, and should they be large-scale general LLMs that are tweaked lightly, or vertical models with baked-in understanding of the vertical they are trying to serve.
An article on this might be very useful to many people.
It is because the real way to make money from AI is to use it to distract, brainwash, confuse, and make poeple think they need something when they don't. So, everyone wants a slice of that pie. Plus, large corporations know that if they create a general-purpose AI then it will be the perfect drug to further distract us from their unsustainable practices.
It'd be interesting to see a direct comparison which would answer the question of "how many less parameters do you need for a targeted vertical model to solve the same problem as a general purpose model".
Like, for example, let's say we pick the task of translating Python to JavaScript, or just any other concrete task: how small could you make a model that only can do this task, vs a general purpose model that can also do this equally well plus a bunch of other things? I wonder if there are any interesting papers tackling this?