Model techniques map
Techniquesmodel architecturemultimodal architecture

general family · filed under model architecture

Two-stage text-then-multimodal pre-training

The first pre-training stage uses text-only data, followed by a multimodal stage.

Also called two-stage pre-training strategy.

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.

We adopt a two-stage pre-training strategy. In the first stage, we train the language backbone on text-only data

usedtraining objectivein MiMo-V2.6Xiaomi

Filed alongside

Other methods under model architecture :: multimodal architecture.