Experimenting primarily with 7B-12B parameter text completion models. Not all models are intended for direct end use, but aim for research and/or educational purposes.
Recent Contributions: stabilized refusal direction ablation via Gram-Schmidt orthonormalization and norm-preserving interventions; confirmed reasoning transfer via model merger.
I think it's clear in retrospect that "frankenmerges", which repeated blocks of layers, amounted to a crude approximation of looped transformers architecture, hence them able to work at all instead of just breaking. They lucked out due to much of the signal passing through residual streams being preserved and only modulated along the way. That said, not all models are suited for this. Models which feature ever-increasing magnitudes as inference progressess through layers risk exploding precision limits.