Cohere

What does Matryoshka representation learning buy a vector-database operator beyond regular embeddings?

Modern vector databases combine sparse (BM25) and dense vectors at the storage layer via two distinct patterns. Identify them.

Doubling the embedding dimension from 768 to 1536 — what changes in storage, query latency, and PQ trainability?

When does binary quantization beat Product Quantization as the production compression choice for a vector index?

Walk through what happens during backprop for a LoRA-wrapped linear layer

LoRA freezes the base weights: does that mean activation checkpointing on the base is unnecessary?

Only 200 examples for a niche format task: which PEFT method gives the best shot?

Match each instruction dataset to its on-disk row shape.

Walk through one training example for SFT'ing a single weather-tool call.

Replay-buffer mix for domain SFT: how much general data, and from where?