Skip to main content

Tokenization and Information Theory

6 selectedDifficulty 3-76 unseenView topic

Saved practice

Keep this quiz in your learner record

Answers count toward your profile, review queue, and next-topic suggestions. You can also use the quick practice below.

FoundationNew
0 answered
1 foundation4 intermediate1 advancedAdapts to your performance
Question 1 of 6
120sfoundation (3/10)conceptual
In language modeling, "bits per byte" (bpb) measures the average bits assigned per byte of text. Why is bpb used instead of perplexity per token?