theron
understanding knowledge structures
Popular repositories Loading
-
crux
crux PublicA 27M transformer processing tokens through recursive gating blocks mid-network while denoising via multi-step discrete diffusion
Python
Repositories
Showing 1 of 1 repositories
- crux Public
A 27M transformer processing tokens through recursive gating blocks mid-network while denoising via multi-step discrete diffusion
TheronAI/crux’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…