GPT, PaLM, Alpaca, Falcon, Vicuna, Claude or something else? 7b, 70b, or 1.7t parameters? Can I host it locally? There's a lot of questions about these models.

We will discuss the overall architecture, the way they are trained, and overall landscape of the LLMs available in the wild. You'll have a much better understanding of what to consider for a particular task.