Large Language Models, Quiz 1
May 2025 term, 13 Jul 2025, Set QDB2
Transformers process input tokens:
One at a time (sequentially)
In reverse order
All at once (in parallel)
Only after seeing the full input
Sign in to report a problem with this question.
You cannot change your answers after submitting.
The palette shows the status of every question. Pick a number to go straight to it.
Transformers process input tokens: What is the purpose of the softmax function in the attention mechanism? What is the main difference between GPT and BERT pre-training objectives?