704: Jon’s “Generative A.I. with LLMs” Hands-on Training — with Jon Krohn (@JonKrohnLearns)

Module Overviews

Jon Krohn introduces his extensive two-hour training on generative AI with large language models (LLMs). The training is divided into four comprehensive modules, starting with an introduction to LLMs, covering the history of natural language processing and key concepts like transformers and auto encoding models. Jon also explores transformer architectures such as Elmo, Bert, T5, and the renowned GPT family 1.

This training is designed to immerse you in the world of large language models, or LLMs for short.

--- Jon Krohn

The second module delves into LLM capabilities, including playgrounds and the progress of the GPT family, especially GPT-4. It also features a demo on calling OpenAI APIs, a crucial skill for data scientists today 1.

   

Multi-GPU Training

The third module is the core of the training, focusing on multi-GPU training, deployment considerations, and monitoring LLMs in production environments. Jon provides insights into hardware options, best practices for efficient LLM training, and selecting and fine-tuning open-source, pre-trained LLMs 2.

This third module provides a thorough understanding of multi GPU training, deployment considerations, and monitoring LLMs in production.

--- Jon Krohn

The final module discusses deriving commercial value from LLMs, including automating tasks and best practices for AI teams. Jon also looks ahead to the future of AI and its societal impact 2.