[paradite]

My burning question: Why not also make a slightly larger model (100B) that could perform even better?

Is there some bottleneck there that prevents RL from scaling up performance to larger non-MoE model?

[t1amat]

See QwQ-Max-Preview: https://qwenlm.github.io/blog/qwq-max-preview/

[buyucu]

they have a larger model that is in previes and still training.