Open Models Almanac
Methodsoptimizationquantization-aware training

single mention · optimization

SFT-Based Quantization-Aware Distillation

Quantization-aware distillation performed using supervised fine-tuning, following a prescribed post-training quantization recipe.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See quantization-aware training for the methods filed beside it.

Also called SFT-based QAD.

Filed under optimization › quantization-aware training