Models and Training

sovereign-mimo-4b

4B parameter code reward model pruned from MiMo-7B. FSM pipeline, ERE gates, WORM sealing. Runs local on RTX 3080.

pythoncudagguf

GitHub →

snapkitty-merged

Nemotron Mini 4.2B GGUF (Q4_K_M). QLoRA fine-tune experiment on sovereign corpus. 2.6 GB.

ggufpython

GitHub →

sovereign-qra

Deterministic routing tensor replacing softmax in MoE dispatch. Zero entropy, proved bijective. Lean 4 zero-sorry.

lean4veriloghaskellcuda

GitHub →

sovlm

Sovereign statistical language model. N-grams, Kneser-Ney smoothing, BM25 retrieval, QRNG sampling.

python

GitHub →

snapkitty-transformer

Corpus classification and training gate with Datalog rules and x86-64 assembly. WORM-sealed receipts.

pythonasmdatalog

GitHub →

sovereign-transformer

Transformer architecture for sovereign inference pipeline with deterministic execution.

python

GitHub →

snapkitty-nemotron

Nemotron fine-tune checkpoint on sovereign domain data.

python

GitHub →

snapkitty-nemotron-harness

Deterministic local harness for Nemotron. EmojiCode persona control, Prolog and Lean gates, sealed receipts.

pythonprologlean4

GitHub →

summon

Pip-installable framework for sovereign fine-tuning. QLoRA, functional API, layered corpus builder, WORM chain sealing.

python

GitHub →

sovereign-gemini-gguf

Zero-dependency GGUF binary parser and neural Graph IR for Gemini-class models without loading weights.

python

GitHub →

nano-gemini

Minimal Gemini model implementation for local inference.

python

GitHub →

pocketlearn

Compact learning framework for on-device model training and inference.

python

GitHub →

lean-llm-starter

Starter kit connecting Lean 4 formal verification with LLM inference pipelines.

lean4python

GitHub →

sovereign-mamba

Mamba SSM architecture integration for sovereign inference with state-space model routing.

pythoncuda

GitHub →

🧠 Models and Training