Rehber bağlantılı sınav · Orta Seviye

LoRA ve Parametre Açısından Verimli Ayarlama Testi

Dondurulmuş LoRA ağırlıklarını, eğitilebilir durum tasarruflarını, sıralamayı, QLoRA depolamayı, uyumlu birleştirmeyi, paylaşılan tabanları, parametre sayımlarını ve çift nicelemeyi inceleyin.

İlgili kılavuz yollarıLora ve Parametre Verimli Ayarlama
Soru 1 arasında 8

In the original LoRA formulation for a selected weight matrix, what is learned while that matrix stays frozen?

Her soruyu önizleyin8 sorular

Testi çözdüğünüzde cevaplar ve açıklamalar görünür.

  1. 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
  2. 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
  3. LoRA bağdaştırıcısındaki 'r' sırası neyi kontrol eder?
    • Adaptör kapasitesini ayarlayan iki düşük dereceli matrisin iç boyutu
    • Temel modeldeki katman sayısı
    • Eğitim sırasında öğrenme oranı
    • Kaç GPU gereklidir?
  4. 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
  5. 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
  6. 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
  7. 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?
    • On altı
    • Sekiz
    • Dört
    • Thirty-two
  8. 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