Kvíz spojený s průvodcem · Střední úroveň
LoRA a kvíz o efektivním ladění parametrů
Prohlédněte si zmrazené váhy LoRA, úspory trénovatelného stavu, hodnocení, úložiště QLoRA, kompatibilní slučování, sdílené báze, počty parametrů a dvojitou kvantizaci.
Otázka 1 z 8
In the original LoRA formulation for a selected weight matrix, what is learned while that matrix stays frozen?
Náhled každé otázky8 otázky
Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.
- In the original LoRA formulation for a selected weight matrix, what is learned while that matrix stays frozen?
- A replacement vocabulary with no weight update
- Every entry of the full base matrix from random initialization
- Two factor matrices forming an additive low-rank update
- A permanent deletion of the entire selected layer
- Which resource requirements can fewer trainable LoRA parameters reduce compared with full fine-tuning?
- Every base-model computation by definition
- All activation storage regardless of the training procedure
- A guaranteed universal percentage of total runtime memory
- Optimizer-state and task-checkpoint requirements
- Co řídí hodnost 'r' v adaptéru LoRA?
- Vnitřní rozměr dvou nižších matic, nastavení kapacity adaptéru
- Počet vrstev v základním modelu
- Rychlost učení během tréninku
- Kolik GPU je potřeba
- Which storage and adaptation choices are combined in the QLoRA paper?
- Updating every base weight directly as a 4-bit integer gradient
- A frozen low-bit base with trainable LoRA adapters
- Removing all adapters and all task data
- A guarantee that every model fits every consumer GPU
- What can a compatible dense merge of a LoRA update remove from that layer's inference computation?
- The need to evaluate the base layer at all
- Every possible dtype compatibility requirement
- A requirement that all future task updates become identical
- The need to evaluate a separate adapter branch
- Which reuse pattern is supported by storing compatible task adapters separately from a base checkpoint?
- Every adapter automatically makes every task factually correct
- All serving systems must switch tasks with zero overhead
- Multiple task updates can share the same pretrained base
- The base checkpoint is no longer needed for inference
- For a stated 4-by-4 weight update with rank-one factors shaped 4-by-1 and 1-by-4, how many factor parameters are there?
- šestnáct
- Osm
- Čtyři
- Třicet dva
- What does QLoRA's double-quantization technique compress in addition to the base weight representation?
- The quantization constants
- Every task label into a second unrelated category
- The adapter gradients twice by definition
- A second complete copy of the base model