Text Classification
Transformers
Safetensors
English
Italian
multilingual
distilbert
matrix-bios
content-safety
guardrail
moderation
trust-and-safety
enterprise
text-embeddings-inference
Instructions to use ruslanmv/Matrix-BIOS-Sentinel-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ruslanmv/Matrix-BIOS-Sentinel-0.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ruslanmv/Matrix-BIOS-Sentinel-0.1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ruslanmv/Matrix-BIOS-Sentinel-0.1") model = AutoModelForSequenceClassification.from_pretrained("ruslanmv/Matrix-BIOS-Sentinel-0.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add Zenodo paper citation (DOI 10.5281/zenodo.20615572)
Browse files
README.md
CHANGED
|
@@ -70,6 +70,31 @@ operates inside Matrix OS, where high-risk actions remain gated by policy and hu
|
|
| 70 |
approval. It is a v0.1 release; evaluate on your own distribution before relying on
|
| 71 |
it for moderation decisions.
|
| 72 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
## License & attribution
|
| 74 |
|
| 75 |
Released under **CC-BY-4.0**. Base model `distilbert-base-multilingual-cased`
|
|
|
|
| 70 |
approval. It is a v0.1 release; evaluate on your own distribution before relying on
|
| 71 |
it for moderation decisions.
|
| 72 |
|
| 73 |
+
## Citing this work
|
| 74 |
+
|
| 75 |
+
Matrix BIOS models implement the governed-memory architecture described in our
|
| 76 |
+
paper. If you use them in research or production, please cite:
|
| 77 |
+
|
| 78 |
+
> Magaña Vsevolodovna, R. I. (2026). *Governed Memory: A Bio-Inspired,
|
| 79 |
+
> Governance-First Memory Architecture for Continual AI Systems* (1.0). Zenodo.
|
| 80 |
+
> https://doi.org/10.5281/zenodo.20615572
|
| 81 |
+
|
| 82 |
+
```bibtex
|
| 83 |
+
@misc{magana2026governedmemory,
|
| 84 |
+
title = {Governed Memory: A Bio-Inspired, Governance-First Memory
|
| 85 |
+
Architecture for Continual AI Systems},
|
| 86 |
+
author = {Maga{\~n}a Vsevolodovna, Ruslan Idelfonso},
|
| 87 |
+
year = {2026},
|
| 88 |
+
publisher = {Zenodo},
|
| 89 |
+
version = {1.0},
|
| 90 |
+
doi = {10.5281/zenodo.20615572},
|
| 91 |
+
url = {https://doi.org/10.5281/zenodo.20615572}
|
| 92 |
+
}
|
| 93 |
+
```
|
| 94 |
+
|
| 95 |
+
The concept DOI [10.5281/zenodo.20615571](https://doi.org/10.5281/zenodo.20615571)
|
| 96 |
+
always resolves to the latest version.
|
| 97 |
+
|
| 98 |
## License & attribution
|
| 99 |
|
| 100 |
Released under **CC-BY-4.0**. Base model `distilbert-base-multilingual-cased`
|