Dataset Size and Quality

Fine-Tune vs Prompting vs RAG

What is Fine-Tuning

Adapters and Prefix/Prompt Tuning

DPO and Preference Alignment

QLoRA and Quantized Fine-Tuning

Preparing Training Datasets

Instruction Fine-Tuning (SFT)

Train/Validation/Test Splits

LoRA (Low-Rank Adaptation)

RLHF

Full vs Parameter-Efficient Fine-Tuning