Week 2, Question 1

Course Q&A Generative AI with Large Language Models
1

Can anyone help me to understand the answer for this question please?
Fill in the blanks: __________ involves using many prompt-completion examples as the labeled training dataset to continue training the model by updating its weights. This is different from _________ where you provide prompt-completion examples during inference.

Pre-training, Instruction fine-tuning
In-context learning, Instruction fine-tuning
Prompt engineering, Pre-training
Instruction fine-tuning, In-context learning

2

I believe this is:

Instruction fine-tuning involves using many prompt-completion examples as the labeled training dataset to continue training the model by updating its weights. This is different from In-context learning where you provide prompt-completion examples during inference.

Not 100% sure thought but I think this makes more sense.

1 Like