03 · ADAPTER

Verified

LoRA and QLoRA

Adapt a frozen base with a low-rank update that fits measurable work into the 16 GB class.

LoRA trains only A and B adapters in W' = W + scale × BA. Initializing B at zero starts from the base model's behavior.

QLoRA stores the frozen base in 4-bit form while adapters and critical computation can use higher precision. It expands the feasible space but never guarantees a specific model fits in 16 GB.

01

First thought

QLoRA trains the entire model as 4-bit integers.

02

Correction

The frozen base is 4-bit; small LoRA adapters are trained and compute precision is handled separately.

03

Decision rule

On 16 GB, start with QLoRA; decide quality with an independent benchmark.