Model techniques map
Techniquespost-trainingpolicy distillation

specific method · filed under post-training

Distillation Fine-Tuning on MiMo-Generated Data

Fine-tuning a model on data generated by MiMo.

Also called trained on MiMo-generated data.

source
1
models
2
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

a Qwen3.5-9B fine-tune trained on MiMo-generated data

usedunclearin MiMo-V2.6-Distill-Qwen-9BXiaomi

Filed alongside

Other methods under post-training :: policy distillation.