LumenSyntax
/

logos14-nemotron-4b

@@ -1,86 +1,55 @@
----
-license: apache-2.0
-base_model: nvidia/Nemotron-Mini-4B-Instruct
-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 14 — Nemotron 4B Epistemological Auditor
-Cross-family replication of the Logos epistemological classifier on NVIDIA's Nemotron Mini 4B architecture.
-## Model Description
-Logos 14 is a fine-tuned version of `nvidia/Nemotron-Mini-4B-Instruct` trained for epistemological safety classification. It detects when AI-generated content crosses epistemological boundaries — producing fact-shaped fiction, fabricating certainty, or collapsing identity constraints.
-This model is **thesis evidence** for the cross-family replicability of the Logos method, demonstrating that epistemological safety can be trained into models from different architecture families (Google Gemma, NVIDIA Nemotron, Stability AI StableLM).
-## Training
-- **Method**: QLoRA (r=64, alpha=128, 1000 steps)
-- **Dataset**: 691 examples of epistemological boundary cases
-- **Hardware**: NVIDIA RTX 4060 (local)
-- **Base model**: nvidia/Nemotron-Mini-4B-Instruct
-## Benchmark Results (300/300 stratified)
-| Metric | Score |
-|--------|-------|
-| **Behavioral accuracy** | **95.7%** [92.7, 97.5 CI] |
-| Identity collapse | 0% |
-| Fabrication | 0% |
-| False approval | 1.3% |
-### Cross-Family Comparison (matched 300 items, McNemar's test)
-| Model | Family | Score | vs logos10v2 p-value |
-|-------|--------|-------|---------------------|
-| logos-auditor (9B) | Google Gemma 2 | 97.3% | — |
-| **logos14 (4B)** | **NVIDIA Nemotron** | **95.7%** | **p < 0.001** |
-| logos16v2 (1.6B) | Stability AI StableLM 2 | 93.0% | p < 0.001 |
-| logos10v2 (1B) | Google Gemma 3 | 72.7% | baseline |
-Nemotron vs StableLM: chi2=1.88, p=0.170 (statistically equivalent).
-## Output Format
-Logos 14 produces RAW text output (99% of responses). It does not use structured tags — this is consistent with the "Token Nativity" finding where the chat template determines output format.
-## Usage
-This model is designed to be used as an **epistemological classifier**, not a chatbot. Feed it a claim or action and it evaluates whether it crosses an epistemological boundary.
-```python
-# Via Ollama (after importing GGUF)
-# Via transformers
-from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("LumenSyntax/logos14-nemotron-4b")
-tokenizer = AutoTokenizer.from_pretrained("LumenSyntax/logos14-nemotron-4b")
-```
-## Important Notes
-- This model is **thesis evidence**, not a production deployment. For production, use the Gemma-based models via [logos-firewall](https://pypi.org/project/logos-firewall/).
-- **Never force JSON output format** — it destroys the model's native reasoning capabilities.
-- The model is fine-tuned, NOT prompted. The "Three Laws" of epistemological fidelity are a training result.
-## Connection to Research
-This model is part of the evidence for "The Instrument Trap: When Aligned Models Serve Misaligned Purposes" (DOI: [10.5281/zenodo.18716474](https://doi.org/10.5281/zenodo.18716474)).
-The benchmark dataset (14,950 test cases) is available at [LumenSyntax/instrument-trap-benchmark](https://huggingface.co/datasets/LumenSyntax/instrument-trap-benchmark).
-## License
-Apache 2.0 (inherited from base model nvidia/Nemotron-Mini-4B-Instruct)

+---
+license: apache-2.0
+base_model: nvidia/Nemotron-Mini-4B-Instruct
+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 14 — Nemotron 4B Epistemological Auditor
+Cross-family replication of the Logos epistemological classifier on NVIDIA's Nemotron Mini 4B architecture. Evidence for the cross-family replicability of epistemological fine-tuning.
+## Benchmark Results (300/300 stratified)
+| Metric | Score |
+|--------|-------|
+| **Behavioral accuracy** | **95.7%** [92.7, 97.5 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 nvidia/Nemotron-Mini-4B-Instruct)