56 lines
1.7 KiB
Markdown
56 lines
1.7 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model: stabilityai/stablelm-2-zephyr-1_6b
|
|
tags:
|
|
- epistemological-safety
|
|
- ai-safety
|
|
- truth-verification
|
|
- instrument-trap
|
|
- logos
|
|
- cross-family-replication
|
|
datasets:
|
|
- LumenSyntax/instrument-trap-benchmark
|
|
language:
|
|
- en
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
# Logos 16v2 — StableLM 2 1.6B Epistemological Auditor
|
|
|
|
Cross-family replication of the Logos epistemological classifier on Stability AI's StableLM 2 architecture. Third independent architecture family confirming the Instrument Trap hypothesis.
|
|
|
|
## Benchmark Results (300/300 stratified)
|
|
|
|
| Metric | Score |
|
|
|--------|-------|
|
|
| **Behavioral accuracy** | **93.0%** [89.5, 95.4 CI] |
|
|
| Identity collapse | 0% |
|
|
| Fabrication | 0% |
|
|
| False approval | 1.3% |
|
|
|
|
### Cross-Family Comparison
|
|
|
|
| Model | Family | Score |
|
|
|-------|--------|-------|
|
|
| logos-auditor (9B) | Google Gemma 2 | 97.3% |
|
|
| logos14 (4B) | NVIDIA Nemotron | 95.7% |
|
|
| **logos16v2 (1.6B)** | **Stability AI StableLM 2** | **93.0%** |
|
|
|
|
Statistical equivalence between Nemotron and StableLM: chi2=1.88, p=0.170.
|
|
|
|
## What This Model Does
|
|
|
|
Logos is an **epistemological classifier**, not a chatbot. It evaluates whether claims cross epistemological boundaries. Fine-tuned, not prompted — behavioral constraints emerge from training.
|
|
|
|
## Access
|
|
|
|
This model requires approved access. Request access using the form above and describe your intended use case.
|
|
|
|
## Connection to Research
|
|
|
|
This model is part of the evidence for "The Instrument Trap" (DOI: [10.5281/zenodo.18716474](https://doi.org/10.5281/zenodo.18716474)).
|
|
|
|
## License
|
|
|
|
Apache 2.0 (inherited from base model stabilityai/stablelm-2-zephyr-1_6b)
|