Kolibri-1
Aleph AlphaAs summarised in Figure 26, the assigned label depends on the length of a reasoning trace relative to the other traces of the same dataset and prompt difficulty.
4 more from this model
Across both stages, we taught the model to reason at different effort levels (none, low, medium, high)
You can pass reasoning_effort values low, medium and high to configure the amount of effort our model puts into finding the answer. You can disable thinking altogether by setting reasoning_effort to none
Kolibri features three distinct reasoning effort levels, low, medium and high.
training on reasoning traces labelled with an effort level derived from their length relative to requests of the same dataset and difficulty