Collections

Kyro-n1.1 is an improved model in the Kyro family with better reasoning than n1. This model outperforms Kyro-n1 in all areas such as STEM: Open-Neo

TokenButler -- Predict token importance for all heads across the transformer in the first layer itself. Enable fine-grained token sparsity!

Romansetu is a collection of models address the challenge of extending Large Language Models (LLMs) to non-English languages using non-Latin scripts

Dataset Collection of Skywork-R1V