πŸ›οΈ qu_ssm (QU-SSM-60M-MoE): Continuous Quasi-Unitary State Space Model with Sparse Mixture-of-Experts

DOI License: CC BY-NC-ND 4.0 Model: qu_ssm-60Moe Flagship: qu_ssm-130Moe

qu_ssm-60Moe (QU-SSM-60M-MoE) is the mid-tier foundation model of the qu_ssm family designed and invented by Prannessh K.V.A. (Sole Architect & Inventor). It combines continuous Lie-group unitary recurrence on SO(2) β‰… U(1) with 4 SwiGLU Mixture-of-Experts (MoE) and Top-2 routing (44.64M active parameters per token).


πŸ” What is qu_ssm?

qu_ssm is a linear-time continuous sequence engine that replaces the monotonic dissipative decay (e^(-Ξ±Β·t) β†’ 0) of classical state space models (Mamba-1/2) with non-dissipative SO(2) unitary phase rotations (β€–R(ΞΈ)β€–β‚‚ ≑ 1.00000), delivering strictly constant O(1) inference memory and sub-millisecond step latency.


πŸ“Š Architecture Specifications

Specification Value
Model Name qu_ssm-60Moe (QU-SSM-60M-MoE)
Sole Architect & Inventor Prannessh K.V.A.
Total Parameters 64.30M
Active Parameters / Token 44.64M (Top-2 Sparse MoE)
Hidden Dimension (D) 384
Layers 6
SSM State Dimension 8
Expert Count 4 SwiGLU Experts
Vocabulary 50,257 (GPT-2 BPE)
Inference State RAM 0.19 MB (Constant O(1))

πŸ”’ Intellectual Property & Citation

  • Sole Architect & Inventor: Prannessh K.V.A.
  • Official Research DOI: 10.5281/zenodo.22217820
  • License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

πŸ”— Related qu_ssm Hub Repositories

Downloads last month
330
Safetensors
Model size
64.3M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Dataset used to train Prannesshkva/QU-SSM-60M-MoE

Space using Prannesshkva/QU-SSM-60M-MoE 1