This workshop focuses on the basics of working with Large Language Models (LLMs) as part of the research pipeline, including understanding and interrogating the models themselves as well as interacting with their generative capabilities. Specific topics will include: setting up your own open-source LLM, fine-tuning LLMs, interacting with LLMs programmatically via an API, and the basics of prompt engineering.

If you have registered for the week-long Natural Language Processing for Data Science workshop (June 10-14) you do NOT need to separately register for this workshop as a seat has automatically been reserved for you.

Prerequisites

This workshop is designed for researchers from all domains with prior programming experience. Basic Python and command-line (shell) skills are required.

Instructors will distribute a zipped directory of notebooks and files the week prior to the workshop. Participants are required to load this data into their Google Drive account before our first session.

Prior to attending this workshop participants should be able to:

• Load text data into Python
• Load Python libraries
• Work with different Python data structures (strings, lists, dictionaries)
• Implement control flow with for loops
• Use Pandas DataFrames (primarily: indexing and subsetting)

Can't make it to this training? Check out upcoming workshop schedule. Recordings of prior workshops are also available in DataLab's training archive.