lora
Applied AI interview questions tagged lora, across every topic.
4 questions · 0 unlocked for you
Concepts behind "lora"
The curriculum that explains the ideas these questions test.
Core
LoRA and Parameter-Efficient Fine-TuningFull fine-tuning updates all of a model's weights, which is expensive in compute and memory and produces a full-size copy per task. LoRA freezes the base model and trains small low-rank adapter matrices, cutting trainable parameters by orders of magnitude while matching most of full fine-tuning's quality. QLoRA adds 4-bit base quantization to fit huge models on one GPU. Applied-AI interviews probe it because PEFT is how teams actually fine-tune, and because LoRA adapters enable serving hundreds of variants cheaply.🧠 Foundations of LLMs & GenAISign in
Core
Catastrophic Forgetting and Continual LearningCatastrophic forgetting is when training a neural network on new data erodes capabilities it already had, because gradient updates overwrite the weights that encoded old skills. Applied AI interviews probe it because fine-tuning a model on a narrow task is the most common way teams accidentally break a general model, and knowing the mitigations (data replay, regularization, parameter-efficient methods) separates people who have shipped fine-tunes from people who have only read about them.📊 Evaluation & ML FoundationsSign in
Core
Multi-LoRA ServingLoRA adapters are tiny weight deltas on top of a shared base model, so you can serve hundreds of fine-tuned variants from one set of base weights instead of one full model per tenant. The serving challenge is batching requests that use different adapters in the same forward pass, swapping adapters in and out of GPU memory on demand, and sharing the base model's KV cache machinery. Applied-AI interviews probe it because it is the economics behind per-tenant and per-task customization and the serving-side complement to LoRA training.🖥️ ML Infrastructure & ServingSign in