Text Classification
Transformers
ONNX
Safetensors
English
modernbert
rag
governance
hallucination-detection
epistemic-honesty
classification
fitz-gov
pyrrho
text-embeddings-inference
Instructions to use yafitzdev/pyrrho-nano-g1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yafitzdev/pyrrho-nano-g1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="yafitzdev/pyrrho-nano-g1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("yafitzdev/pyrrho-nano-g1") model = AutoModelForSequenceClassification.from_pretrained("yafitzdev/pyrrho-nano-g1") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ A drop-in replacement for the constraint+sklearn governance pipeline in [fitz-sa
|
|
| 41 |
|
| 42 |
Validated on the [fitz-gov](https://github.com/yafitzdev/fitz-gov) V5.1 eval split (584 cases, stratified 20% hold-out from `tier1_core`). All numbers are **3-seed mean ± std** across seeds [42, 1337, 7].
|
| 43 |
|
| 44 |
-
| Metric | pyrrho
|
| 45 |
|---|---|---|---|
|
| 46 |
| Overall accuracy (calibrated) | **86.13 ± 0.86** | 78.7 | **+7.43** |
|
| 47 |
| False-trustworthy rate (safety) | **5.27 ± 0.21** | 5.7 | **-0.43** (safer) |
|
|
@@ -170,7 +170,7 @@ fitz-gov commit at training time: `3e1d22e22fdff726330a0d70503b07f73dacf817`
|
|
| 170 |
## Citation
|
| 171 |
|
| 172 |
```bibtex
|
| 173 |
-
@misc{
|
| 174 |
title = { pyrrho-nano-g1 },
|
| 175 |
author = { Yan Fitzner },
|
| 176 |
year = { 2026 },
|
|
|
|
| 41 |
|
| 42 |
Validated on the [fitz-gov](https://github.com/yafitzdev/fitz-gov) V5.1 eval split (584 cases, stratified 20% hold-out from `tier1_core`). All numbers are **3-seed mean ± std** across seeds [42, 1337, 7].
|
| 43 |
|
| 44 |
+
| Metric | pyrrho-nano-g1 | fitz-sage v0.11 (sklearn baseline) | Δ |
|
| 45 |
|---|---|---|---|
|
| 46 |
| Overall accuracy (calibrated) | **86.13 ± 0.86** | 78.7 | **+7.43** |
|
| 47 |
| False-trustworthy rate (safety) | **5.27 ± 0.21** | 5.7 | **-0.43** (safer) |
|
|
|
|
| 170 |
## Citation
|
| 171 |
|
| 172 |
```bibtex
|
| 173 |
+
@misc{pyrrho_nano_g1_2026,
|
| 174 |
title = { pyrrho-nano-g1 },
|
| 175 |
author = { Yan Fitzner },
|
| 176 |
year = { 2026 },
|