ATRIUMsearch → argument graph
DefinitionArticle

Knowledge distillation trains a separate, smaller model to copy the behavior of a larger one, producing a genuinely new model rather than a compressed version of the original.

Distillation produces a separate model with its own parameters, unlike compression methods like quantization and pruning which shrink an existing model. ✦ AI generated

Author · ByteByteGo Newsletter · 2026-08-05 · original ↗

Distillation trains a new, smaller model to copy the behavior of a larger one. The setup involves two models: The first is a large, capable model called the teacher. The second is a smaller model called the student, which is trained to reproduce the teacher's outputs. Once training finishes, the student runs on its own, and the teacher steps out of the picture. A common assumption is that the student is the teacher in compressed form. The reality, however, is different. Compression methods such as quantization and pruning start with one model and reduce its footprint by storing its numbers at lower precision or removing parts that contribute little to the result. The model stays the same model, smaller and lighter. Distillation, on the other hand, produces a genuinely separate model, with its own parameters and often a different design, whose goal during training is to behave like the teacher. One operation shrinks an existing model. The other trains a fresh one.

Read full article ↗excerpt · fair-use quotation

Around this claim