Instructions to use SNAPKITTYWEST/sovereign-memory-twin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SNAPKITTYWEST/sovereign-memory-twin with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SNAPKITTYWEST/sovereign-memory-twin")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SNAPKITTYWEST/sovereign-memory-twin", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SNAPKITTYWEST/sovereign-memory-twin with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SNAPKITTYWEST/sovereign-memory-twin"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SNAPKITTYWEST/sovereign-memory-twin",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SNAPKITTYWEST/sovereign-memory-twin

SGLang

How to use SNAPKITTYWEST/sovereign-memory-twin with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SNAPKITTYWEST/sovereign-memory-twin" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SNAPKITTYWEST/sovereign-memory-twin",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SNAPKITTYWEST/sovereign-memory-twin" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SNAPKITTYWEST/sovereign-memory-twin",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SNAPKITTYWEST/sovereign-memory-twin with Docker Model Runner:
```
docker model run hf.co/SNAPKITTYWEST/sovereign-memory-twin
```

Sovereign Memory Twin (RMTN)

Recurrent Memory Twin Network - Evidence/Silence verdict protocol, WORM-sealed, IBM i ledger integrated.

SnapKitty West / SNAPKITTYWEST - Evidence or Silence - 2026

Model Description

Returns cryptographically sealed verdicts (EVIDENCE or SILENCE) over financial documents and compliance queries.

WORM-sealed: every verdict is SHA256(verdict | score | query | timestamp)
No third state: EVIDENCE or SILENCE only
Trust Deed governance: Bel Esprit D Accord Trust Deed v1.0 (six articles)
Evidence threshold: score >= 0.42
IBM i bridge: native RPGLE/COBOL FSL/DB2 integration
NATS mesh: publishes to snapkitty.bifrost.sealed

Trust Deed Articles

Article	Rule
I	Identity
II	Truth Mandate - no output without evidence
III	Compliance Protocol - required fields enforced
IV	Verdict Format - strict JSON only
V	Evidence Threshold - score >= 0.42
VI	Human Review Guarantee - SILENCE routes to queue

Integration

bob-orchestrator validate server (port 7474)
DEVFLOW-FINANCE ERP (Stripe, Prisma, ledger)
IBM i RPGLE + DB2 (POSTTRAN / REVTRAN / ADJTRAN)
NATS snapkitty.bifrost.sealed

Papers - 11 Total (8 Zenodo + 3 In-Repo LaTeX)

File	Lines	Venue	Title
gdr_kernels.tex	460	SC / MLSys	GDR-9: Formally Verified Generalized Delta Rule Kernel Stack Across Nine ISAs
liquidops_kernel.tex	566	PLDI / ICFP	LiquidOps: Refinement-Verified NAND-Canonical Kernel for Data-Plane ISA Compilation
sovereign_entropy.tex	394	FM / CAV	Sovereign Entropy: Formally Verified 0.20-Nat Bound for Deterministic Agent Outputs

GDR-9 - Nine-ISA kernel stack (CUDA, NASM, RISC-V, ARM, WASM, APL, Haskell, Lean 4, P4). Generalized delta rule + drain invariants. Cross-ISA equivalence proved in Lean 4. Target: SC/MLSys.

LiquidOps - NAND-canonical verified compiler. LiquidHaskell refinement types enforce correctness end-to-end. P4 backend. Target: PLDI/ICFP.

Sovereign Entropy - Lean 4 machine-checked proof: routing entropy H(alpha) <= 0.20 nats. SPARK Ada contract + ERE gate. Governs BURT-IMMA router and sovereign-memory-twin verdict threshold. Target: FM/CAV.

Zenodo (8 papers, published 2026-07-01) - PIRTM, octonions, Coxeter/Weyl, PH-DAE, EmojiScript, Goldilocks, Resonance disclosure, DMZ F2 decomposition. DOIs in sovereign-engine-v2 README.

License

Apache-2.0

Downloads last month: -

SNAPKITTYWEST
/

sovereign-memory-twin