NAiOS IconNAiOS Logo
NAiOS Wiki

Model Distillation

También: Model Distillation · Knowledge Distillation · Knowledge Distillation · Teacher-Student Model

Compressing a large model into a small one while preserving quality

1 min de lectura

Model distillation is a training technique that transfers the knowledge from a large and expensive model (the teacher) to a smaller and more efficient one (the student). Instead of training the small model solely with the original labels, it learns to mimic the teacher's outputs, including its probability distributions (so-called soft labels), which contain richer information about the relationship between classes.

This technique matters because it allows models to be deployed in resource-constrained environments —mobile, browsers, or edge devices— without sacrificing too much quality. Its main advantages are:

  • Lower inference cost and energy consumption.
  • Faster response speed.
  • Lighter models that are easier to distribute.

A practical example is DistilBERT, a reduced version of BERT that maintains around 97% of its performance with approximately 40% fewer parameters. It is worth noting that distillation rarely preserves 100% of the quality: there is a trade-off between size and precision that must be adjusted according to the use case.

¿Quieres profundizar?

Lee nuestros artículos sobre IA aplicada en el blog de NAiOS.

Ir al Blog