Chapter 3 · Quiz

Generative model architecture

Choose one answer per question. Each explanation links back to the relevant section.

01 Why does word count fail to determine context size?
02 In a causal grid, which keys can a query at position 3 read?
03 Why keep tokenization identical when comparing perplexities?
04 With probabilities 0.60, 0.25, 0.10 and 0.05 and top-p = 0.80, which options should be kept?
05 Which test is useful for multimodal extraction of a scanned table?