README.md

---
license: apache-2.0
language:
- de
- en
base_model:
- patronus-studio/husky-sight-tool-type-classifier
pipeline_tag: text-classification
tags:
- tool-use
- ai-agents
- function-calling
- mcp
- tool-security
- security
- llm-security
- ai-safety
- ai-agent-security
- patronus
- multilingual
- modernbert
- onnx
- quantized
- edge
---

# Model Card for Husky Sight Tool Type Classifier Edge

**Quantized ONNX builds of [Husky Sight Tool Type Classifier](https://huggingface.co/patronus-studio/husky-sight-tool-type-classifier) for local / edge inference.**

This repository contains the size- and memory-optimized ONNX exports of the FP32 model. For
intended uses, class definitions, training data, benchmarks, and limitations, see the
[main model card](https://huggingface.co/patronus-studio/husky-sight-tool-type-classifier).

## Variants

| Variant | Path | Quantization |
| --- | --- | --- |
| FP16 | `onnx/fp16/model.onnx` | FP16 weights |
| INT8 | `onnx/int8/model.onnx` | Post-training dynamic INT8 (MatMul/Gemm) |
| INT8 + INT4 embeddings | `onnx/int8_int4_embeddings/model.onnx` | Dynamic INT8 plus 4-bit weight-only token embeddings |

The exact quantization parameters are recorded in `onnx/quantization_manifest.json`.

## Benchmark

Quantization parity on the unified_v3 held-out test split (n = 2914; max_length 128, CPU):

| Variant | Accuracy | F1 (macro) | Δ F1 vs FP32 |
| --- | --- | --- | --- |
| FP32 reference (main repo) | 0.9568 | 0.9567 | — |
| FP16 | 0.9557 | 0.9554 | -0.0013 |
| INT8 | 0.9574 | 0.9573 | +0.0006 |
| INT8 + INT4 embeddings | 0.9550 | 0.9548 | -0.0019 |

Measured CPU latency (batch 64): ~18.89 ms/text for the INT8+INT4 build.

Full details in `metrics/quant_bench.json`.

## Usage

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

model_id = "patronus-studio/husky-sight-tool-type-classifier-edge"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = ORTModelForSequenceClassification.from_pretrained(model_id, subfolder="onnx/int8_int4_embeddings")

inputs = tokenizer("...", return_tensors="pt")
logits = model(**inputs).logits
```

Post-process the logits as described in the main model card (softmax over the logits, argmax).

## License

Released under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0); the full
text is included as `LICENSE`. Derived from
[Husky Sight Tool Type Classifier](https://huggingface.co/patronus-studio/husky-sight-tool-type-classifier) and ultimately from
[jhu-clsp/mmBERT-small](https://huggingface.co/jhu-clsp/mmBERT-small) (MIT License); upstream
notices are retained.

## Patronus Ark

This model is built to run inside **Patronus Ark**, Patronus' open-source on-device
AI-security scanning library (L1 native rules → L2 NTDB cascade → L3 transformer).
Ark is not publicly released yet — a repository link will be added here at launch.

---

## 🛡️ Patronus Protect

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

Try it for free at [patronus.studio](https://patronus.studio).