> Note: we are not releasing any post-trained / IT checkpoints.
I get not trying to cannibalize Gemma, but that's weird. A 540M multimodel model that performs well on queries would be useful and "just post-train it yourself" is not always an option.
This made me compare the figures, and: did they accidentally switch those around, or are the Post-training Reasoning and Factuality scores actually significantly lower than the Pre-training ones?
Edit: Just noticed
> Also note pre-training and post-training benchmarks are different, so scores are not comparable across plots.
They are comparing 1B Gemma to 1+1B T5Gemma 2. Obviously a model with twice more parameters can do more better. Says absolutely nothing about benefits of the architecture.
7 comments
[ 2.9 ms ] story [ 26.5 ms ] threadI get not trying to cannibalize Gemma, but that's weird. A 540M multimodel model that performs well on queries would be useful and "just post-train it yourself" is not always an option.
Edit: Just noticed
> Also note pre-training and post-training benchmarks are different, so scores are not comparable across plots.
The paper gives more details about the specific benchmarks and the scores obtained in them: https://arxiv.org/html/2512.14856v1#S4
don't care. prove effective context length or gtfo.