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
|
@@ -21,7 +21,7 @@ metrics:
|
|
| 21 |
- false-trustworthy-rate
|
| 22 |
---
|
| 23 |
|
| 24 |
-
# pyrrho-
|
| 25 |
|
| 26 |
> Decide whether your retrieved sources support a confident answer, contradict each other, or simply don't contain it — **without an LLM call**.
|
| 27 |
|
|
@@ -68,8 +68,8 @@ Validated on the [fitz-gov](https://github.com/yafitzdev/fitz-gov) V5.1 eval spl
|
|
| 68 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 69 |
import torch
|
| 70 |
|
| 71 |
-
tokenizer = AutoTokenizer.from_pretrained("yafitzdev/pyrrho-
|
| 72 |
-
model = AutoModelForSequenceClassification.from_pretrained("yafitzdev/pyrrho-
|
| 73 |
|
| 74 |
query = "Has the company achieved profitability?"
|
| 75 |
contexts = [
|
|
@@ -99,9 +99,9 @@ For production CPU inference at ~30 ms / case, load the INT8 ONNX variant via `o
|
|
| 99 |
from optimum.onnxruntime import ORTModelForSequenceClassification
|
| 100 |
from transformers import AutoTokenizer
|
| 101 |
|
| 102 |
-
tokenizer = AutoTokenizer.from_pretrained("yafitzdev/pyrrho-
|
| 103 |
model = ORTModelForSequenceClassification.from_pretrained(
|
| 104 |
-
"yafitzdev/pyrrho-
|
| 105 |
file_name="model_quantized.onnx",
|
| 106 |
)
|
| 107 |
# Same input format as above...
|
|
@@ -171,10 +171,10 @@ fitz-gov commit at training time: `3e1d22e22fdff726330a0d70503b07f73dacf817`
|
|
| 171 |
|
| 172 |
```bibtex
|
| 173 |
@misc{pyrrho_v1_2026,
|
| 174 |
-
title = { pyrrho-
|
| 175 |
author = { Yan Fitzner },
|
| 176 |
year = { 2026 },
|
| 177 |
-
url = { https://huggingface.co/yafitzdev/pyrrho-
|
| 178 |
}
|
| 179 |
```
|
| 180 |
|
|
|
|
| 21 |
- false-trustworthy-rate
|
| 22 |
---
|
| 23 |
|
| 24 |
+
# pyrrho-nano-g1
|
| 25 |
|
| 26 |
> Decide whether your retrieved sources support a confident answer, contradict each other, or simply don't contain it — **without an LLM call**.
|
| 27 |
|
|
|
|
| 68 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 69 |
import torch
|
| 70 |
|
| 71 |
+
tokenizer = AutoTokenizer.from_pretrained("yafitzdev/pyrrho-nano-g1")
|
| 72 |
+
model = AutoModelForSequenceClassification.from_pretrained("yafitzdev/pyrrho-nano-g1").eval()
|
| 73 |
|
| 74 |
query = "Has the company achieved profitability?"
|
| 75 |
contexts = [
|
|
|
|
| 99 |
from optimum.onnxruntime import ORTModelForSequenceClassification
|
| 100 |
from transformers import AutoTokenizer
|
| 101 |
|
| 102 |
+
tokenizer = AutoTokenizer.from_pretrained("yafitzdev/pyrrho-nano-g1")
|
| 103 |
model = ORTModelForSequenceClassification.from_pretrained(
|
| 104 |
+
"yafitzdev/pyrrho-nano-g1",
|
| 105 |
file_name="model_quantized.onnx",
|
| 106 |
)
|
| 107 |
# Same input format as above...
|
|
|
|
| 171 |
|
| 172 |
```bibtex
|
| 173 |
@misc{pyrrho_v1_2026,
|
| 174 |
+
title = { pyrrho-nano-g1 },
|
| 175 |
author = { Yan Fitzner },
|
| 176 |
year = { 2026 },
|
| 177 |
+
url = { https://huggingface.co/yafitzdev/pyrrho-nano-g1 },
|
| 178 |
}
|
| 179 |
```
|
| 180 |
|