Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 138
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets Paper • 2201.02177 • Published Jan 6, 2022 • 6
Termius minimal Collection A model made to deal with the bash only tasks, suitable for diverse cases. • 2 items • Updated May 22