Tutorvo

Token Budgets & Dashboard: Tokens per Toy Document, Cost at a Fictional Price per 1,000 Tokens and a Chart

Lesson 8 of 817 minLab

This lesson is part of the course

In this lesson

You turn word counts into input and output tokens for five toy documents, price each run at fictional rates per 1,000 tokens, add up the monthly cost, check the context limit and chart tokens per word by document type.

Buy the course once for $9.99 to unlock every lesson and lab, the final exam and the certificate – lifetime access, no subscription.

Lessons in this course

  1. Characters and Frequencies: A Toy Word List, Characters per Word and the Starting VocabularyLab14 min Locked
  2. Pair Counts: Adjacent Pairs per Word, One Token per Cell, Weighted by Word FrequencyLab15 min Locked
  3. The First Merge: Rewriting Every Word with IF on Neighbouring Cells and Closing the GapsLab17 min Locked
  4. Several Merges: A Merge Table, the Vocabulary After Each Step and Tokens per Word ShrinkingLab15 min Locked
  5. Tokenizing New Words: Applying the Merges in Order, Unknown Characters and FallbacksLab16 min Locked
  6. Compression: Tokens per Word, Characters per Token and the Effect of More MergesLab14 min Locked
  7. Vocabulary Trade-offs: Vocabulary × Embedding Width = Parameters, Sequence Length vs Vocabulary SizeLab15 min Locked
  8. Token Budgets & Dashboard: Tokens per Toy Document, Cost at a Fictional Price per 1,000 Tokens and a ChartLab17 min Locked