Pre-training, Data, Fine-tuning & Alignment
Fine-tuning in Practice: SFT, LoRA and QLoRA
When to fine-tune, how parameter-efficient methods work and how to evaluate the result.
Advanced 25 min For: Developers ✎ In progress
✎ This lesson is still being written. Below is the planned outline; it is not indexed by search engines yet.
What this lesson will cover
- Fine-tune vs prompt vs RAG
- Supervised fine-tuning data
- LoRA and QLoRA
- Evaluating a fine-tuned model