Designing Large Language Model Applications

Chapter 5. Adapting LLMs to Your Use Case

In this chapter, we will continue with our journey through the LLM landscape, exploring the various LLMs available for commercial use and providing pointers on how to choose the right LLM for your task. We will also examine how to load LLMs of various sizes and run inference on them. We will then decipher various decoding strategies for text generation. We will also investigate how to interpret the outputs and intermediate results from language models, surveying interpretability tools like LIT-NLP.

Navigating the LLM Landscape

Seemingly a new LLM is being released every few days, many claiming to be state of the art. Most of these LLMs are not very different from each other, so you need not spend too much time tracking new LLM releases. This book’s GitHub repository attempts to keep track of the major releases, but I don’t promise it will be complete.

Nevertheless, it is a good idea to have a broad understanding of the different types of LLM providers out there, the kinds of LLMs being made available, and the copyright and licensing implications. Therefore, let’s now explore the LLM landscape through this lens and understand the choices at our disposal.

Who Are the LLM providers?

LLM providers can be broadly categorized into the following types:

Companies providing proprietary LLMs

These include companies like OpenAI (GPT), Google (Gemini), Anthropic (Claude), Cohere, AI21, etc. that train proprietary LLMs and make them available as ...