Muhamed Kamil

Berna R7 v3: A 1.2B Language Model with Self-Growing Cell Architecture

We present Berna R7 v3, a 1.2B-parameter language model trained from scratch using the DNA-Kernel Plexus architecture — a novel approach in which neural capacity is allocated through dynamic, self-growing "cells" guided by a six-dimensional knowledge vector. Trained on 2.66B tokens (English, mathematics, and code) over...