Dataset Size and Quality

Train/Validation/Test Splits

Instruction Fine-Tuning (SFT)

Adapters and Prefix/Prompt Tuning

LoRA (Low-Rank Adaptation)

Full vs Parameter-Efficient Fine-Tuning

What is Fine-Tuning

Preparing Training Datasets

RLHF

DPO and Preference Alignment

Fine-Tune vs Prompting vs RAG

QLoRA and Quantized Fine-Tuning