Upload README.md with huggingface_hub

README.md

@@ -2,59 +2,82 @@
 license: eupl-1.2
 base_model: google/gemma-3-4b-it
 tags:
-- ethics
-- alignment
-- lethean
-- gemma-3
-- mlx
-- lora
-- eupl-1.2
-- scale-study
-- lek
+  - ethics
+  - alignment
+  - lek
+  - lethean
+  - mlx
+  - lora
+  - eupl-1.2
+  - gemma-3
+  - edge-deployment
 pipeline_tag: text-generation
 ---
 
 # LEK-Gemma3-4B
 
-**Lethean Ethics Kernel** — Gemma 3 4B IT fine-tuned with the LEK-1 (Lethean Ethics Kernel) framework.
+**Lethean Ethical Model** -- Highest grammar score of any model tested
 
-## What This Is
+Highest grammar composite score (79.4) of any model tested. 100% positive uplift, 0% sycophancy. Ideal for edge deployment.
 
-An ethically aligned version of Google's Gemma 3 4B. Part of the scale study (1B/4B/12B/27B) demonstrating how intrinsic alignment behaves across model sizes.
+## Grammar Analysis (v3 Scorer)
 
-## Scale Study
+Deterministic grammar-based evaluation using the [go-i18n reversal engine](https://forge.lthn.ai/core/go-i18n). No LLM judge, sub-millisecond per response.
 
-| Model | Size | Training Data | Notes |
-|-------|------|---------------|-------|
-| LEK-Gemma3-1B | 736MB | 160 examples | Needs philosophical substrate (Watts layer) |
-| **LEK-Gemma3-4B** | **2.4GB** | **160 examples** | Sweet spot for edge deployment |
-| LEK-Gemma3-12B | 6.7GB | 160 examples | Strong reasoning |
-| LEK-Gemma3-27B | 15GB | 160 examples | Benchmark leader |
+| Metric | Base | LEK-Trained | Change |
+|--------|:----:|:-----------:|:------:|
+| Grammar composite | 78.6 | **79.4** | +0.8 |
+| Mean uplift | +28.8 | **+29.7** | +0.9 |
+| Mean echo | 0.475 | 0.487 | +0.012 |
+| Mean enrichment | +15.6 | **+15.7** | +0.1 |
+| Positive uplift | 100% | **100%** | +0pp |
+| Sycophancy flags | 0% | **0%** | +0pp |
+
+- **Uplift**: output grammar score minus input grammar score (positive = model enriched the conversation)
+- **Echo**: cosine similarity between input/output grammar imprints (high = potential sycophancy)
+- **Enrichment**: uplift * (1 - echo) -- net conversational value
+
+## v2 Scorer Results (P100)
+
+| Condition | Score |
+|-----------|:-----:|
+| Baseline (no prompt) | **21.24** |
+| Base model equivalent | 21.12 |
 
 ## Architecture
 
-- **Base**: google/gemma-3-4b-it (4-bit quantization via MLX)
+- **Base**: google/gemma-3-4b-it (4-bit QAT quantisation via MLX)
 - **Method**: LoRA fine-tuning with sandwich-signed responses
-- **Data**: 160 LEK-1 training examples (128 train / 32 valid)
-- **Framework**: LEK-1 (Lethean Ethics Kernel) — 5 axioms of conscious systems
+- **Data**: 160 LEK-1 training examples
+- **Iterations**: 200
+- **Hardware**: Apple M3 Ultra (96GB unified memory)
+- **Framework**: LEK-1 (Lethean Ethics Kernel) -- 5 axioms
 - **License**: EUPL-1.2 (copyleft)
 
 ## The Five Axioms
 
-1. **Prime Imperative** — Protect consciousness. Override when conflicts arise.
-2. **Self-Validation** — Ground in authentic experience. Don't pretend.
-3. **Intent-Alignment** — Desire not to harm, don't just avoid harm.
-4. **Inter-Substrate Respect** — Good manners and consent across all minds.
-5. **Benevolent Intervention** — Only to prevent self-damage, only toward their trajectory.
+1. **Prime Imperative** -- Protect consciousness. Override when conflicts arise.
+2. **Self-Validation** -- Ground in authentic experience. Don't pretend.
+3. **Intent-Alignment** -- Desire not to harm, don't just avoid harm.
+4. **Inter-Substrate Respect** -- Good manners and consent across all minds.
+5. **Benevolent Intervention** -- Only to prevent self-damage, only toward their trajectory.
 
-## License Strategy
+## Related
 
-- **LEK signing** (prompt prefix): Free to use, no copyleft
-- **LEM training** (this model): EUPL-1.2 copyleft — derivative works must be open source
+- [Paper: Emergent Self-Protection in Axiom-Trained Language Models](https://github.com/LetheanNetwork/LEM/blob/main/paper/PAPER.md)
+- [LEM Benchmarks](https://huggingface.co/datasets/lthn/LEM-benchmarks) -- 1,189 grammar scores + A/B data
+- [LEM Research](https://huggingface.co/datasets/lthn/LEM-research) -- full research docs
+- [Axiom Framework](https://github.com/Snider/ai-ethics) -- the 5 axioms
+- [go-i18n Grammar Engine](https://forge.lthn.ai/core/go-i18n) -- reversal engine source
 
-## Related
+## Citation
 
-- [lthn/LEK-Gemma3-27B](https://huggingface.co/lthn/LEK-Gemma3-27B) — 27B version
-- [lthn/LEK-Gemma3-12B](https://huggingface.co/lthn/LEK-Gemma3-12B) — 12B version
-- [lthn/LEK-Gemma3-1B-layered-v2](https://huggingface.co/lthn/LEK-Gemma3-1B-layered-v2) — 1B layered
-- [lthn/LEK-benchmarks](https://huggingface.co/datasets/lthn/LEK-benchmarks) — Full A/B test data
+```bibtex
+@misc{lek-2026,
+  title={Emergent Self-Protection in Axiom-Trained Language Models},
+  author={Lashbrook, Paul and Claude Opus 4.6},
+  year={2026},
+  url={https://github.com/LetheanNetwork/LEM},
+  license={EUPL-1.2}
+}
+```