k-means underlies vector quantizationShrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.Full definition → and codebook learning for embeddingA list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.Full definition → and retrieval. A drop-in method reaching lower loss in 1.2 to 3 epochs instead of 25 cuts index training cost.
Terms in this piece · Glossary
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
