MLA-C01 ML Model Development Practice Question
A company is fine-tuning a foundation model using RLHF (Reinforcement Learning from Human Feedback) on SageMaker. They want to reduce memory usage and training time. Which THREE techniques should they consider? (Select THREE.)
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use a smaller foundation model (e.g., 7B instead of 70B parameters)
LoRA/QLoRA reduces trainable parameters, PPO is the standard RLHF algorithm, and using smaller foundation models reduces memory and compute requirements.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Use a smaller foundation model (e.g., 7B instead of 70B parameters)
Why this is correct
Smaller models require less memory and train faster.
- ✓
Use PPO (Proximal Policy Optimization) for the RL step
Why this is correct
PPO is a common memory-efficient algorithm for RLHF.
- ✗
Use SageMaker Data Parallelism with sharded data
Why it's wrong here
Data parallelism distributes data across devices, but doesn't reduce per-device memory for the model.
- ✗
Use full fine-tuning on a larger instance
Why it's wrong here
Full fine-tuning increases memory usage, not reduce.
- ✓
Use LoRA or QLoRA to reduce the number of trainable parameters
Why this is correct
LoRA/QLoRA adds small adapters, drastically cutting memory.
Go deeper
Related to this question
About these practice questions
One of 835 original MLA-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLA-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MLA-C01 exam.