The tower desk both extra-trains a small language model on last decade’s logbooks and still retrieves tonight’s weather bulletin into the prompt. What should the tester know?
Select an answer to reveal the explanation.
Short Explanation
Extra-training a small language model on last decade's logbooks and still retrieving tonight's weather bulletin into the prompt is allowed. A pretrained model may use RAG, fine-tuning, or both. They are alternatives that can also be combined.
Full Explanation
RAG and fine-tuning can be used alone or together on the same pretrained core. Forbidding the combination or substituting a Chapter 5 lab misses that fact.