← Generative AI and LLMs
Lesson 3 of 4
Adapting LLMs
Watch, read the card, then practise. Fine-tuning · Prompting or fine-tuning
The video for this lesson is being recorded.
Meanwhile, the notes below and the 60-second cards cover the same ideas.
Practise this topicFine-tuning
Fine-tuning trains a pre-trained model further on your own examples, so a style or skill becomes built in.
Remember: Fine-tune behaviour and format, not fast-changing facts.
Prompting or fine-tuning
Try prompting first, add retrieval for facts, and fine-tune only when those can't reach the quality you need.
Remember: Prompt → RAG → fine-tune, in that order.