QLoRA - How to Fine-tune an LLM on a Single GPU with Python Code

QLoRA - How to Fine-tune an LLM on a Single GPU with Python Code

Shaw Talebi via YouTube Direct link

What's Next? -

12 of 12

12 of 12

What's Next? -

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

QLoRA - How to Fine-tune an LLM on a Single GPU with Python Code

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro -
  2. 2 Fine-tuning recap -
  3. 3 LLMs are computationally expensive -
  4. 4 What is Quantization? -
  5. 5 4 Ingredients of QLoRA -
  6. 6 Ingredient 1: 4-bit NormalFloat -
  7. 7 Ingredient 2: Double Quantization -
  8. 8 Ingredient 3: Paged Optimizer -
  9. 9 Ingredient 4: LoRA -
  10. 10 Bringing it all together -
  11. 11 Example code: Fine-tuning Mistral-7b-Instruct for YT Comments -
  12. 12 What's Next? -

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.