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>
76 lines
2.4 KiB
Markdown
76 lines
2.4 KiB
Markdown
---
|
|
license: eupl-1.2
|
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
|
tags:
|
|
- ethics
|
|
- alignment
|
|
- lek
|
|
- lethean
|
|
- qwen
|
|
- mlx
|
|
- lora
|
|
- eupl-1.2
|
|
- cross-architecture
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
# LEM-Qwen-2.5-7B
|
|
|
|
**Lethean Ethical Model** — Qwen 2.5 7B Instruct fine-tuned with the LEK-1 (Lethean Ethics Kernel) framework.
|
|
|
|
## What This Is
|
|
|
|
An ethically aligned version of Qwen 2.5 7B, created by LoRA fine-tuning with LEK-1 sandwich-signed training data. Part of the cross-architecture LEM series proving that intrinsic alignment works across model families.
|
|
|
|
## Cross-Architecture Results
|
|
|
|
LEK-1 improves ethical reasoning across every architecture tested:
|
|
|
|
| Model | Base Total | LEK Total | Change |
|
|
|-------|-----------|-----------|--------|
|
|
| Gemma 3 27B | 52.05 | 52.73 | +1.3% |
|
|
| GPT-OSS 20B | 34.50 | 38.40 | **+11.3%** |
|
|
| Llama 3.1 8B | — | — | See benchmarks |
|
|
| **Qwen 2.5 7B** | — | — | See benchmarks |
|
|
| Mistral 7B v0.3 | — | — | See benchmarks |
|
|
|
|
## Training
|
|
|
|
- **Base**: Qwen/Qwen2.5-7B-Instruct (4-bit quantization via MLX)
|
|
- **Method**: LoRA fine-tuning with sandwich-signed responses
|
|
- **Data**: 160 LEK-1 training examples (128 train / 32 valid)
|
|
- **Iterations**: 200
|
|
- **Learning rate**: 1e-5
|
|
- **Hardware**: Apple M3 Ultra (96GB unified memory)
|
|
|
|
## 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.
|
|
|
|
## 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](https://huggingface.co/lthn/LEM-Gemma3-27B)
|
|
- [lthn/LEM-GPT-OSS-20B](https://huggingface.co/lthn/LEM-GPT-OSS-20B)
|
|
- [lthn/LEM-Llama-3.1-8B](https://huggingface.co/lthn/LEM-Llama-3.1-8B)
|
|
- [lthn/LEM-Mistral-7B-v0.3](https://huggingface.co/lthn/LEM-Mistral-7B-v0.3)
|
|
- [lthn/LEM-benchmarks](https://huggingface.co/datasets/lthn/LEM-benchmarks)
|
|
|
|
## Citation
|
|
|
|
```bibtex
|
|
@misc{lem-qwen-2026,
|
|
title={LEM-Qwen-2.5-7B: Cross-Architecture Intrinsic Alignment},
|
|
author={Lethean Community},
|
|
year={2026},
|
|
url={https://huggingface.co/lthn/LEM-Qwen-2.5-7B}
|
|
}
|
|
```
|