Chapter AD10-C02 · Adaptation, compression, and advanced-model judgment
Tuning and efficiency
Explain different objectives and resource requirements; Compare efficiency gains against quality losses.
Units in this chapter
- AD10-U03 Fine-tuning, LoRA, and alignment overview Explain different objectives and resource requirements
- AD10-U04 Quantization, distillation, and serving Compare efficiency gains against quality losses
Reading that connects these units
Reading
- PEFT documentation Parameter-efficient adaptation; inspect requirements before attempting training.About this reference (W23)
- LoRA: Low-Rank Adaptation of Large Language Models Low-rank parameter updates, experimental setup, and assumptions.About this reference (P03)
- PEFT Inspect a LoRA example and resource requirements; execution is an optional advanced lab.About this reference (G07)
- Hugging Face LLM Course Transformers, tokenization, model use, datasets, and adaptation.About this reference (W22)
- Transformers Inspect model examples and inference/training entry points for a pinned environment.About this reference (G06)
- AI Engineering Application patterns, evaluation, and system-level tradeoffs; select AI Engineering on the author page.About this reference (B09)
Selected, not required. Reviewed 2026-11-17.