Classifying with small models · Module B of 6
Labels and representation
What does the model see, and what does it promise to return?
Labels as an API contract, the text features that came before embeddings, and how to pick an encoder without trusting a leaderboard.
Topics in this module
Topics
🔒 Unlocks at 4 of 4 topics in Phase 1 — 0 done.- B1
Labels and label encoding Planned
Labels are the model’s API contract; encoding turns them into numbers.
- B2
TF-IDF Planned
Word weights that favour rare words, with no notion of synonyms.
- B3
Choosing an encoder Planned
Four families, the raw-BERT trap, contrastive training, retrieval vs similarity.
- B4
Model cards and bake-offs Planned
Filter by hard limits, then test on your own data.