Nybble™
SnackStackHack
Embeddings, End to End

Lesson 8 of 23

Lessons

  1. 1. The problem embeddings solve
  2. 2. A coordinate system for meaning
  3. 3. Reading a real embedding
  4. 4. What makes an embedding good
  5. 5. One-hot vectors and the bag of words
  6. 6. TF-IDF, and how far counting can take you
  7. 7. word2vec: meaning from company
  8. 8. GloVe, and fastText's fix for unknown words
  9. 9. The context problem: ELMo and BERT
  10. 10. Sentence-BERT and the contrastive turn
  11. 11. Where embeddings sit inside an LLM
  12. 12. What is the difference between an LLM and an embedding model?
  13. 13. How modern embedding models are trained
  14. 14. Fine-tuning, part 1: getting the data right
  15. 15. Fine-tuning, part 2: the training run
  16. 16. Embeddings in action
  17. 17. Every modality: images, audio and video
  18. 18. Embeddings as graphs
  19. 19. The other embeddings, and what they are all for
  20. 20. How to choose an embedding model
  21. 21. MTEB, and how to read a leaderboard
  22. 22. Evaluation metrics for embeddings
  23. 23. Embeddings in RAG, and shipping them
  24. Key takeaways
  25. How to get certified
  26. Your certificate

GloVe, and fastText's fix for unknown words

Free account

Read this lesson

The opening lessons of every course are free — this one needs an account. Sign in and the full course opens.

  • Every lesson, start to finish
  • Progress saved across devices
  • Bits per lesson, plus a bonus for finishing

Free · your email is used for progress only.

Nybble™ — built for the people building AI.

AboutTermsPrivacyContact
SnackStackHack
Message Nybble