Open Models Almanac
Methodspost-trainingpolicy distillation

single mention · post-training

Multiple-Teacher Distillation

Multiple-teacher distillation provides high, medium, and low reasoning-effort modes.1 This method allows users to control the trade-off between token consumption and performance.2

Trade-off Users can control the trade-off between token consumption and performance.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. Multiple-teacher distillation provides high, medium, and low reasoning-effort modes — technical report
  2. allowing users to control the trade-off between token consumption and performance — technical report

Filed under post-training › policy distillation