Model techniques map
Techniquespost-trainingpolicy distillation

specific method · filed under post-training

Large-Scale On-Policy Distillation

On-policy distillation trained across all domains using over 40 teacher models.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

As the last stage of post-training, the final full-vocabulary OPD task is trained on datasets from all domains using over 40 teacher models.

usedpost trainingin DeepSeek-V4.1DeepSeek

the final full-vocabulary OPD task is trained on datasets from all domains using over 40 teacher models.

usedpost trainingin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

Other methods under post-training :: policy distillation.