Nybble™
SnackStackHack
Embeddings, End to End

Course wrap-up

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

Your certificate

Certificates are issued to an account — it's what ties the credential to a name a reader can check. Sign in to see where you stand on Embeddings, End to End.

← PreviousBack to course

Nybble™ — built for the people building AI.

AboutTermsPrivacyContact
SnackStackHack
Message Nybble