This chapter covers
- Defining small language models
- Limits and risks of using closed source generalist LLMs
- Open source alternatives to closed source LLMs
- Comparing LLMs and domain-specific language models
Whenever a new, potentially disruptive technology emerges, or an existing one undergoes a radical change, there’s inevitable hype about it. If expectations aren’t met, interest can drop quickly; if they are, investments and projects can surge before the real business potential and risks are understood. Either way, the “next big thing” rarely ends well. You can see the same thing happening today with large language models (LLMs): there’s so much hype that it’s difficult to understand what they really can (and can’t) do and whether they would be a good fit for your own business needs. This chapter aims to clarify the LLM world by highlighting the pros, risks, and challenges of both generalist and domain-specific models. Hype is the one thing you won’t find in this book.