MODULE 3B · OPTIONAL · DAY 1
Customizing Models with LoRA / QLoRA
Make the model yours, reproducibly, in a container
Gourav Shah · School of DevOps & AI · GPU-gated · Hands-on
M3B·01
What you'll learn
M3B·02
1 · When to fine-tune — and when not to
M3B·03
The problem: a behaviour gap
A behaviour gap, not a knowledge gap
M3B·04
Prompt vs RAG vs fine-tune
Pick the cheapest tool that closes the gap
M3B·05
2 · LoRA — sticky notes on a textbook
M3B·06
LoRA, sticky notes on a textbook
Freeze the textbook, add sticky notes
M3B·07
QLoRA, squeeze the base to 4-bit
Quantize the base so a 7B fits one GPU
M3B·08
The open-source toolchain
One toolchain, split by hardware
M3B·10
4 · The GPU reality
M3B·11
The same GPU reality, again
Native on Mac, containerized on NVIDIA
M3B·12
5 · Reproducibility — the frozen container is the experiment
M3B·13
The frozen container is the experiment
Scripts rot, a pinned image doesn't
M3B·14
6 · What you produce — and where it fits
M3B·15
What you produce: a tiny adapter
One tiny adapter, three ways to use it
M3B·16
The pipeline, end to end
One more step in the pipeline you own
M3B·17
TO THE LAB
Two tracks, one destination: a working adapter
Fine-tune the behaviour, keep the base
Optional module — do it if your cohort needs model customization. · Gourav Shah · School of DevOps & AI
M3B·18