We took a 30B model and split it in two to write tokens in parallel instead of one at a time.
Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch.
We found it kept 98.7% of the original model’s quality at 2.42× faster generation.
We must build our own, open-source, decentralized, distributed AGI
there is no other way.
right now politicians and big tech executives are holding us hostage
they literally hold our future in their hands
this HAS to change.