Raoul Harris
  • Introduction
  • Technical books
    • Data engineering with Alteryx
    • Deep learning in Python
    • Generative AI in action
    • Generative deep learning
    • Outlier analysis
    • Understanding deep learning
    • Understanding machine learning: from theory to algorithms (in progress)
    • Review: Deep learning: foundations and concepts
  • Technical courses
    • Advanced SQL Server masterclass for data analytics
    • Building full-stack apps with AI
    • Complete Cursor
    • DataOps methodology
    • DeepLearning.AI short courses
    • Generative AI for software development
      • Introduction to generative AI for software development
      • Team software engineering with AI
      • AI-powered software and system design
    • Generative AI with large language models
    • Generative pre-trained transformers
    • IBM DevOps and software engineering
      • Introduction to agile development and scrum
      • Introduction to cloud computing
      • Introduction to DevOps
    • Machine learning in production
    • Reinforcement learning specialization
      • Fundamentals of reinforcement learning
      • Sample-based learning methods
      • Prediction and control with function approximation
  • Non-technical books
    • Management skills for everyday life (in progress)
  • Non-technical courses
    • Business communication and effective communication specializations
      • Business writing
      • Graphic design
      • Successful presentation
      • Giving helpful feedback (not started)
      • Communicating effectively in groups (not started)
    • Illinois Tech MBA courses
      • Competitive strategy (in progress)
    • Leading people and teams specialization
      • Inspiring and motivating individuals
      • Managing talent
      • Influencing people
      • Leading teams
Powered by GitBook
On this page
  1. Technical courses

DeepLearning.AI short courses

Improving the accuracy of LLM applications

Practical examples in this course were based on using Llama 3 with the Lamini library.

  • Start with rigorous evaluation and iterating the prompt

  • If adjusting the prompt isn't enough then try fine-tuning

  • Fine-tuning often doesn't require much data

  • Parameter-efficient fine-tuning can be very cheap

  • Memory tuning allows you to embed specific facts directly into the model

    • I haven't independently researched whether this is actually useful or just Lamini marketing

  • Evaluation dataset

    • Start small

    • Quality > Quantity

    • Focus on the areas that it does poorly on

    • Try to find the easiest examples that still fail

    • Try to break the process to identify issues

    • Set an accuracy target

    • Iterate the dataset as performance improves

  • Scoring using LLMs

    • You would ideally use a deterministic approach instead if practical

    • Ask for a numerical score

    • Use a structured output to enforce this

    • Can you provide a reference answer for it to score against?

  • Rolling your own fine-tuning can be hard, so consider managed fine-tuning

    • Inefficient implementations

    • Idle compute due to not being able to parallelize efficiently

    • Crashes

  • Consider using LLMs to help create fine-tuning datasets

Last updated 7 months ago