Mastery card
I can explain LoRA
A lighter way to fine-tune by training small adapter layers.
LoRA (Low-Rank Adaptation) fine-tunes small adapter matrices instead of all model weights, reducing compute and storage for customisation.
Sticky trick
LoRA = sew a small patch, don't reweave the whole sweater.
Take into the room
In plain English, what is LoRA?
Or open the share card 🧵
Or start your own 5-word trail from home.