Classifying with small models · Module F of 6
Beyond bi-encoders, and shipping
What do I reach for when similarity is not enough, and how do I ship it?
Reading two texts together, two-stage retrieval, and getting a small model onto real hardware without the answers drifting.
Topics in this module
Topics
🔒 Unlocks at 1 of 1 topics in Module C — 0 done.- F1
NLI and cross-encoders Planned
Read both texts together; zero-shot labels via hypotheses.
- F2
Retrieve, then rerank Planned
A fast filter and a careful judge, measured by recall@k.
- F3
Shipping small models Planned
ONNX, int8 quantization and parity fixtures.