RMSN-347M-Bulk-Tube-SFT
Resonant Metriplectic Sheaf Network β 6-Layer Bulk Waveguide Tube Topology Fine-tuned on DuoNeural reasoning traces (CoT SFT, 15k steps).
Architecture
| Parameter | Value |
|---|---|
| Hidden dim | 1280 |
| Layers | 16 |
| Workspace slots | 64 |
| Params | 346.53M |
| Framework | Port-Hamiltonian (αΈ = {f,H} + [f,S]) |
| Tokenizer | HuggingFaceTB/cosmo2-tokenizer (vocab=49152) |
Soliton Topology: 6-Layer Bulk Waveguide Tube
Layer PR Role
ββββββββββββββββββββββββββββββββββββββββββ
L00 ~40 Input (diffuse)
L01 ~45 ...
...
L07 ~15 Pre-tube buffer
L08 1.00 β
MACROSCOPIC CORE (dual singularity)
L09 1.00 β
MACROSCOPIC CORE (dual singularity)
L10 ~3.5 Tube interior
L11 ~4.1 Tube interior
L12 ~5.2 Tube interior
L13 ~2.8 Tube terminus
L14 ~18 Post-tube buffer
L15 ~35 Output (diffuse)
ββββββββββββββββββββββββββββββββββββββββββ
Topological class: Bulk Waveguide Tube β continuous 6-layer soliton [L8βL13] Ξ»_max: Global Lyapunov distributed across tube (no single cascade signal) Key property: Forgetting-Shield β bulk topology screens foundational weights from SFT gradient injection. Best-ever wiki retention at 5k SFT steps (ppl=176.01).
Quantum-Classical Correspondence
BlueQubit QCPU quantum circuit simulation (DuoNeural Phase 5):
| Metric | Value |
|---|---|
| S_boundary / S_bulk | 0.569 |
| Predicted bulk width | 7β8 layers |
| Classical bulk width | 6 layers (L8βL13) |
| Quantum-classical error | <8% |
S_boundary/S_bulk = 0.569 places D=1280 between D=1024 (0.632) and D=1536 (0.515), consistent with the Topological Bulk Shield Law: wider D β more bulk entanglement absorption.
SFT Benchmark Results (15k steps)
| Steps | wiki_ppl β | cot_ppl β |
|---|---|---|
| 5k | 176.01 π best-ever | 13.82 |
| 10k | 199.77 | 11.24 |
| 15k (best ckpt) | 208.68 | 10.77 |
SFT loss record: 1.4798 (all-time DuoNeural lab best as of Nov 10 2026) Lyapunov stability: 100% stable throughout SFT (Ξ» < 0 at all checkpoints)
Optimal SFT Depth
The dual-core topology creates more SFT attack surface than a pointlike soliton. Optimal SFT for D=1280 β 5β7k steps. Crossover with single-core topologies at ~7.5k steps. Law: Ξβ_wiki β exp(βΞL_tube/ΞΎ) where ΞΎ contracts as N_steps grows.
Quickstart
import torch
from rmsn_core import RMSNForCausalLM, RMSNConfig
config = RMSNConfig(vocab_size=49152, hidden_dim=1280, num_layers=16,
num_workspace_slots=64, max_seq_len=512)
model = RMSNForCausalLM(config)
ck = torch.load("model.pt", map_location="cpu")
model.load_state_dict(ck["model_state"])
model.eval()
Citation
@misc{duoneural2026rmsn,
title={Resonant Metriplectic Sheaf Networks: Port-Hamiltonian Language Models with Soliton Waveguide Topology},
author={DuoNeural Lab and Archon and Aura},
year={2026},
note={DuoNeural Phase 5 β Bulk Tube Topology}
}
DuoNeural Lab | Phase 5: Tube Topology Zoo | Nov 2026
- Downloads last month
- 36