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
Four ideas: when to fine-tune, what LoRA does, which tool to use
M3B·02
The problem: a behaviour gap
No prompt reliably fixes this. That's not a knowledge gap.
M3B·03
Prompt vs RAG vs fine-tune
Three tools, three gaps. Reach for the cheapest one that closes yours.
M3B·04
LoRA — sticky notes on a textbook
Can't rewrite the expensive textbook — so add Post-it notes in the margins
M3B·05
QLoRA — squeeze the base to 4-bit
Quantize the frozen base to 4-bit and a 7B fits one consumer GPU
M3B·06
The open-source toolchain
A handful of mature stacks cover almost every fine-tuning job
M3B·07
The same GPU reality — again
Native on Apple Silicon, containerized on NVIDIA — never the reverse
M3B·08
The frozen container is the experiment
Scripts rot — Python, PEFT, bitsandbytes drift. An OCI image does not.
M3B·09
What you produce: a tiny adapter
A 50–200 MB adapter directory — two small files, ready to serve
M3B·10
The pipeline, end to end
Fine-tuning is one rung — it feeds serving and packaging you know
M3B·11
TO THE LAB
Two tracks, one destination: a working adapter
Fine-tune the behaviour · keep the base · ship the tiny adapter
Optional module — do it if your cohort needs model customization. · Gourav Shah · School of DevOps & AI
M3B·12