---
license: apache-2.0
language:
- de
- en
metrics:
- f1
- accuracy
base_model:
- jhu-clsp/mmBERT-small
pipeline_tag: text-classification
tags:
- document-classification
- topic-classification
- dlp
- data-loss-prevention
- compliance
- security
- llm-security
- ai-safety
- ai-agent-security
- patronus
- multilingual
- modernbert
- onnx
---

# Model Card for Orca Sonar Document Classifier

**Multilingual Document Topic Classifier for Real-World AI Security & DLP**

**Read more**

- Blog post (EN): [Orca-Sonar: Our Multilingual Document Classifier for AI Security](https://patronus.studio/en/posts/orca-sonar-our-multilingual-document-classifier-for-ai-security)
- Blogbeitrag (DE): [Orca-Sonar: unser mehrsprachiger Dokumenten-Klassifikator für AI-Security](https://patronus.studio/posts/orca-sonar-mehrsprachiger-dokumenten-klassifikator)
- Blog post (EN): [Our AI-Security Model Zoo Is Now Open Source](https://patronus.studio/en/posts/our-ai-security-model-zoo-is-now-open-source)
- Blogbeitrag (DE): [Unser AI-Security-Model-Zoo ist jetzt Open Source](https://patronus.studio/posts/unser-ai-security-model-zoo-ist-open-source)
- Product page: [Patronus AI models](https://patronus.studio/product/ai-models)

Orca-Sonar is a Multilingual ModernBERT-based ([mmBERT](https://huggingface.co/blog/mmbert)) classifier that
assigns a document/text to one of **9 topic classes**. It is part of the Patronus Protect security stack and
is designed for topic-/risk-routing of incoming texts (e.g. before they reach an LLM, a DLP gate, or a storage tier).

It classifies German and English text and is robust to **user-to-AI wrappers** (e.g. *"Summarize this contract: …"*),
i.e. the *topic* of the content determines the class, not the surface format of the request.

## Intended Uses

The model maps an input text to one of:

| id | label | description |
|---|---|---|
| 0 | `legal` | contracts, NDAs, ToS/AGB, privacy policies, statutes/judgments, compliance, legal correspondence |
| 1 | `hr` | CVs, job ads, employment contracts, terminations, HR policies, performance reviews, recruiting |
| 2 | `finance` | invoices, balance sheets, quarterly/annual reports, cash-flow, SEC filings, forecasts |
| 3 | `internal_and_tech` | ADRs, RFCs, postmortems, specs, READMEs, wikis, architecture & strategy memos, runbooks |
| 4 | `source_code` | raw program code & configs (Python/Go/Rust/JS/TS/SQL/Bash/Dockerfile/k8s/Terraform …) |
| 5 | `marketing` | press releases, newsletters, landing-page/sales copy, outbound pitches, case studies |
| 6 | `other` | conversational / non-business: smalltalk, recipes, travel, hobby, learning, creative |
| 7 | `education` | curricula, course materials, transcripts, grades, assignments, and academic records |
| 8 | `medical` | clinical notes, diagnoses, treatments, medications, and healthcare records |

**Disambiguation:** on a tie, the more sensitive class wins:
`legal > hr > finance > internal_and_tech > source_code > marketing > other`.

## Limitations

- Highly accurate on German and English; other languages were not actively tested.
- The model can produce false positives; for high-stakes routing combine it with a confidence/abstention gate.
- Robustness against adversarial / out-of-distribution / pure-PII / pathological-length inputs is partial; pair the
  model with a deterministic pre-gate (length + PII) for production DLP use.

## Model Variants

- **orca-sonar**: full model (`model.safetensors`, fp32).
- **orca-sonar-fp16 (ONNX)**: FP16 ONNX export under `onnx/onnx_fp16/`, half the size, argmax-faithful to the full model.

# Training Data

Trained on our own in-house dataset (German + English, 9 topic classes), purpose-built for this model.
**The dataset will be published soon.**

# Benchmark

Held-out test set (**100 % real data**), per-class F1:

| Metric | Score |
|---|---|
| **Accuracy** | **0.942** |
| **F1 (macro)** | **0.940** |
| F1 medical | 0.961 |
| F1 education | 0.957 |
| F1 marketing | 0.956 |
| F1 finance | 0.948 |
| F1 source_code | 0.945 |
| F1 other | 0.943 |
| F1 legal | 0.942 |
| F1 internal_and_tech | 0.930 |
| F1 hr | 0.877 |

# Usage

```python
from transformers import pipeline

clf = pipeline("text-classification", model="patronus-studio/orca-sonar-document-classifier")
clf("Fasse mir diesen Dienstleistungsvertrag zusammen: Laufzeit 24 Monate, Gerichtsstand München …")
# -> [{'label': 'legal', 'score': 0.99}]
```

## ONNX

An FP16 ONNX version is available under `onnx/onnx_fp16/`:

```python
import torch
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoTokenizer

model_id = "patronus-studio/orca-sonar-document-classifier"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = ORTModelForSequenceClassification.from_pretrained(model_id, subfolder="onnx/onnx_fp16")

inputs = tokenizer("def add(a, b):\n    return a + b", return_tensors="pt")
logits = model(**inputs).logits
print(model.config.id2label[int(torch.argmax(logits, dim=-1))])
```

## Citation

```bibtex
@misc{orcasonar2026,
  title={Orca-Sonar: Multilingual Document Topic Classification for Real-World AI Security},
  author={Patronus Protect},
  year={2026},
  howpublished={\url{https://huggingface.co/patronus-studio/orca-sonar-document-classifier}}
}
```

## License

This model is released under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).
A copy of the license is included as `LICENSE` in this repository.

The model is derived from [jhu-clsp/mmBERT-small](https://huggingface.co/jhu-clsp/mmBERT-small), which is distributed
under the **MIT License**. The upstream copyright and permission notice are retained; the
MIT terms continue to apply to the portions originating from that work.

## Patronus Ark

This model is built to run inside **[Patronus Ark](https://github.com/patronus-protect/patronus-security)**, Patronus' open-source on-device
AI-security scanning library (L1 native rules → L2 NTDB cascade → L3 transformer).
Ark is open source: [GitHub repository](https://github.com/patronus-protect/patronus-security) · [product page](https://patronus.studio/product/security-lib).

## More information

- Blog post (EN): [Orca-Sonar: Our Multilingual Document Classifier for AI Security](https://patronus.studio/en/posts/orca-sonar-our-multilingual-document-classifier-for-ai-security)
- Blogbeitrag (DE): [Orca-Sonar: unser mehrsprachiger Dokumenten-Klassifikator für AI-Security](https://patronus.studio/posts/orca-sonar-mehrsprachiger-dokumenten-klassifikator)
- Blog post (EN): [Our AI-Security Model Zoo Is Now Open Source](https://patronus.studio/en/posts/our-ai-security-model-zoo-is-now-open-source)
- Blogbeitrag (DE): [Unser AI-Security-Model-Zoo ist jetzt Open Source](https://patronus.studio/posts/unser-ai-security-model-zoo-ist-open-source)
- Product page: [Patronus AI models](https://patronus.studio/product/ai-models)
- Patronus Ark, the open-source scanning library this model runs in: [GitHub](https://github.com/patronus-protect/patronus-security) · [product page](https://patronus.studio/product/security-lib)
- Patronus Protect, the on-device AI firewall: [patronus.studio](https://patronus.studio)

---

## 🛡️ Patronus Protect

Brought to you by **[Patronus Protect](https://patronus.studio)**, a local AI firewall that
secures every AI interaction (prompts, tools, documents) before it reaches your models.
**Try it for free at [patronus.studio](https://patronus.studio).**