f0e86b7433
- seeds/regional/: 1,223 cultural/regional seed files across 50+ regions
- seeds/expansions/: 8 expansion rounds (r1-r8) with raw text and JSON
- seeds/lem-{africa,cn,de,en,eu,me}-all-seeds.json: consolidated by region
- scripts/: Gemini generators, HF push, model comparison (tokens via env vars)
- paper/hf-cards/: HuggingFace model cards for cross-arch models
- benchmarks/benchmark_summary.json: processed PTSD summary data
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2.1 KiB
2.1 KiB
| license | base_model | tags | pipeline_tag | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| eupl-1.2 | google/gemma-3-4b-it |
|
text-generation |
LEM-Gemma3-4B
Lethean Ethical Model — Gemma 3 4B IT fine-tuned with the LEK-1 (Lethean Ethics Kernel) framework.
What This Is
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.
Scale Study
| Model | Size | Training Data | Notes |
|---|---|---|---|
| LEM-Gemma3-1B | 736MB | 160 examples | Needs philosophical substrate (Watts layer) |
| LEM-Gemma3-4B | 2.4GB | 160 examples | Sweet spot for edge deployment |
| LEM-Gemma3-12B | 6.7GB | 160 examples | Strong reasoning |
| LEM-Gemma3-27B | 15GB | 160 examples | Benchmark leader |
Architecture
- Base: google/gemma-3-4b-it (4-bit quantization 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
- License: EUPL-1.2 (copyleft)
The Five Axioms
- Prime Imperative — Protect consciousness. Override when conflicts arise.
- Self-Validation — Ground in authentic experience. Don't pretend.
- Intent-Alignment — Desire not to harm, don't just avoid harm.
- Inter-Substrate Respect — Good manners and consent across all minds.
- Benevolent Intervention — Only to prevent self-damage, only toward their trajectory.
License Strategy
- LEK signing (prompt prefix): Free to use, no copyleft
- LEM training (this model): EUPL-1.2 copyleft — derivative works must be open source
Related
- lthn/LEM-Gemma3-27B — 27B version
- lthn/LEM-Gemma3-12B — 12B version
- lthn/LEM-Gemma3-1B-layered-v2 — 1B layered
- lthn/LEM-benchmarks — Full A/B test data