Blog & Insights
Deep Learning
Gear & Fitness
Community & Events
About
Gen AI (advanced)
timed Mode
30s remaining
Q 1/13
+0 XP
Multiple Choice
How does Low-Rank Adaptation (LoRA) reduce parameter training requirements during fine-tuning?
It prunes 90% of model layers before backpropagation
It freezes pre-trained model weights and injects trainable rank decomposition matrices (A x B) into attention layers
It quantizes weights to 1-bit integers during forward pass
It replaces self-attention with linear convolutions
Submit Answer
