๐Ÿ›๏ธ qu_ssm (QU-SSM-60M-MoE): Continuous Quasi-Unitary State Space Model with Sparse Mixture-of-Experts

๐Ÿ“„ Official Research Paper (PDF) & Open Verification

Title: "Gated Quasi-Unitary Lie-Algebra Recurrent State Space Models" Author: Prannessh K.V.A. (@prannesshkva)

๐Ÿ“ฅ Download Full Research Paper (PDF) | ๐Ÿ›๏ธ Zenodo DOI: 10.5281/zenodo.22283431 | ๐ŸŽฎ Live Interactive Space

Official Paper Zenodo DOI Tri-License Interactive Space

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) โ‰… U(1) with 4 SwiGLU Mixture-of-Experts (MoE) and Top-2 routing (44.64M active parameters per token).


๐Ÿ” What is qu_ssm?

qu_ssm is a linear-time continuous sequence engine that replaces the monotonic dissipative decay (e^(-ฮฑยทt) โ†’ 0) of classical state space models (Mamba-1/2) with non-dissipative SO(2) unitary phase rotations (โ€–R(ฮธ)โ€–โ‚‚ โ‰ก 1.00000), delivering strictly constant O(1) inference memory and sub-millisecond step latency.


๐Ÿ“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))

๐Ÿ”’ Intellectual Property & Citation

  • Sole Architect & Inventor: Prannessh K.V.A.
  • Official Research DOI: 10.5281/zenodo.22283431
  • License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

๐Ÿ”— Related qu_ssm Hub Repositories

Downloads last month
2,081
Safetensors
Model size
64.3M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

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

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