Deep Learning
Resources
Setup
FAQ
Shakeri Lab
School of Data Science • UVA
11.1 – ICL, Prompt Engineering, and RAG
Slide preview
View Slides
Suggested reading
Brown et al., GPT-3 Few-Shot Learning
Wei et al., Chain-of-Thought Prompting
Lewis et al., Retrieval-Augmented Generation
11.2 – Parameter-Efficient Fine-Tuning (PEFT)
Slide preview
View Slides
Suggested reading
Hu et al., LoRA
Li & Liang, Prefix-Tuning
Liu et al., P-Tuning v2
11.3 – Quantization & QLoRA
Slide preview
View Slides
Suggested reading
Dettmers et al., QLoRA
Frantar et al., GPTQ
Lin et al., AWQ
🧪 Gemma Fine-Tuning
Gemma model card: ai.google.dev/gemma/docs/core/model_card_3
Full Model Fine-Tune (Hugging Face Transformers, Colab)
Fine-Tune with QLoRA (Hugging Face, Guide)
Fine-Tuning with Gemma Library (Colab)
Module 10
Module 12