Stricter token constraints during training

A training approach that imposes stricter token constraints to balance performance and cost.

source: 1
model: 1
lab adopt it: 1
strongest: used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

DeepSeek-V3.2

Evidence

1 span quoted from the sources, strongest treatment first.

we imposed stricter token constraints during the training of the official DeepSeek-V3.2, aiming to optimize the trade-off between performance and cost.

usedoptimizationin DeepSeek-V3.2DeepSeek

paper·DeepSeek

Filed alongside

Other methods under training objective :: language modelling objective.

Cross-entropy objective Fill-in-the-middle (FIM) completion Next-token prediction Sampled-token objective Text pre-training