Oracle Exam 1Z0-1127-24 Topic 2 Question 20 Discussion

Actual exam question for Oracle's 1Z0-1127-24 exam

Question #: 20
Topic #: 2

Which is a distinguishing feature of "Parameter-Efficient Fine-tuning (PEFT)" as opposed to classic Tine- tuning" in Large Language Model training?

APEFT involves only a few or new parameters and uses labeled, task-specific data.

BPEFT modifies all parameters and uses unlabeled, task-agnostic data.

CPEFT does not modify any parameters but uses soft prompting with unlabeled data. PEFT modifies

DPEFT parameters and b typically used when no training data exists.

Show Suggested Answer

Suggested Answer: A

by Joseph at Nov 19, 2024, 06:57 AM

Limited Time Offer

25%

Off

Get Premium 1Z0-1127-24 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Xochitl

2 days ago

Actually, I think PEFT does not modify any parameters but uses soft prompting with unlabeled data.

upvoted 0 times

...

Myong

5 days ago

C) Hmm, I'm not sure that's correct. Doesn't PEFT actually modify the model parameters, not just use soft prompting?

upvoted 0 times

...

Bernadine

5 days ago

I disagree, I believe PEFT modifies all parameters and uses unlabeled data.

upvoted 0 times

...

Jaime

12 days ago

A) Looks like the right answer to me. Modifying only a few parameters and using labeled data sounds like a smart way to fine-tune large language models.

upvoted 0 times

...

Janna

26 days ago

I think the distinguishing feature of PEFT is that it involves only a few new parameters and uses labeled data.

upvoted 0 times

...