Large Language Models and ChatGPT in Three Weeks
A code repository accompanying a paid course, covering LLM architecture, ChatGPT API usage, latency and cost comparisons, and hands-on Jupyter notebooks on prompt engineering.
This repository is the code companion to a course on large language models, focused on OpenAI's and Anthropic's model families. It introduces LLM architecture, strengths and use cases; shows how to call the ChatGPT API and interpret its responses; compares the latency of hosted API calls against locally run models; and includes methods for calculating the cost of API calls from token usage.
The material is organized as a set of Jupyter notebooks, starting with an introduction to prompt engineering, meant to be worked through hands-on rather than only read. It assumes familiarity with Python and requires an OpenAI API key, and existing familiarity with machine learning and natural language processing is described as helpful but not required.