---
title: "gliner2-pii"
publisher: "fastino"
type: "endpoint"
updated: "2026-11-20T00:00:30.763Z"
description: "Extract PII character spans and confidence scores with the Fastino GLiNER2 privacy filter."
canonical: "https://build.nvidia.com/fastino/gliner2-pii"
---

[API Reference](/fastino/gliner2-pii/apireference.md) — Endpoints, authentication, request schemas, and responses.

# fastino/gliner2-pii

## Description
fastino/gliner2-pii detects personally identifiable information (PII) in text across 42 entity types and seven languages. Fastino developed this GLiNER2 fine-tune for identifying sensitive spans that applications can mask or redact.

*This model is ready for commercial or non-commercial use.*

## Third-Party Community Consideration:
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA [fastino/gliner2-pii Model Card](https://huggingface.co/fastino/gliner2-privacy-filter-PII-multi)

## License and Terms of Use:
**GOVERNING TERMS:** Use of this trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). The [gliner2-privacy-filter-PII-multi model](https://huggingface.co/fastino/gliner2-privacy-filter-PII-multi) is available under the [Apache-2.0 License](https://choosealicense.com/licenses/apache-2.0/).

## Deployment Geography:
Global

## Use Case:
**Use Case:** PII detection and masking, data governance, and training-data hygiene in multilingual text pipelines.

## Release Date:
**Build.NVIDIA.com:** 11/16/2026 via [link](https://build.nvidia.com/fastino/gliner2-pii) (planned)  
**Huggingface:** 05/10/2026 via [link](https://huggingface.co/fastino/gliner2-privacy-filter-PII-multi)

## Reference(s):
**References:**

- [Original Fastino model card](https://huggingface.co/fastino/gliner2-privacy-filter-PII-multi)
- [GLiNER2 implementation](https://github.com/fastino-ai/GLiNER2)
- [GLiNER2 model configuration](https://huggingface.co/fastino/gliner2-privacy-filter-PII-multi/blob/1cb4166094dc58fa8d836429f060d6c95f62b495/config.json)
- [GLiNER2-PII technical report](https://arxiv.org/abs/2605.09973)

## Model Architecture:
**Architecture Type:** Transformer  
**Network Architecture:** GLiNER2 (mDeBERTa-v3-base encoder)  
**Total Parameters:** 307.1M  
**Base Model:** GLiNER2

### Input:
**Input Types:** Text  
**Input Formats:** String  
**Input Parameters:** One-Dimensional (1D)  
**Other Input Properties:** Entity labels condition extraction; a subset of the 42 supported labels can be supplied.

### Output:
**Output Types:** Text  
**Output Format:** Other (Structured entity results)  
**Output Parameters:** One-Dimensional (1D)  
**Other Output Properties:** Entity results can include confidence scores and spans; application post-processing performs redaction.

__Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.__

## Software Integration:
**Runtime Engines:**

- **GLiNER2**

For the planned production API, send a `POST` request to the [NVIDIA API endpoint](https://integrate.api.nvidia.com/v1/chat/completions) with `"model": "fastino/gliner2-pii"` in the request body.

**Supported Hardware:**

- **NVIDIA Ampere:** A100
- **NVIDIA Blackwell:** B200
- **NVIDIA Hopper:** H100, H200

**Preferred Operating Systems:** Linux

__The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.__

## Model Version(s)
fastino/gliner2-pii

## Training, Testing, and Evaluation Datasets:

### Training Dataset
**Data Modality:** Text  
**Text Training Data Size:** Undisclosed  
**Training Data Collection:** Synthetic  
**Training Labeling:** Synthetic  
**Training Properties:** Fine-tuning used 4,910 synthetic texts with 129,951 PII mentions, generated with GPT-5.4 (Generative Pre-trained Transformer) at temperature 0.01 using constraint-driven generation. Languages: English, French, Spanish, German, Italian, Portuguese, and Dutch; total training tokens are undisclosed.

### Testing Dataset
**Testing Data Collection:** Undisclosed  
**Testing Labeling:** Undisclosed  
**Testing Properties:** Undisclosed; the vendor does not separately describe an internal testing set's sample count, modalities, content, or language coverage.

### Evaluation Dataset
**Evaluation Data Collection:** Synthetic  
**Evaluation Labeling:** Synthetic  
**Evaluation Properties:** The [SPY: Enhancing Privacy with Synthetic PII Detection Dataset](https://aclanthology.org/2025.naacl-srw.23/) benchmark contains synthetic English text, as identified in its [dataset card](https://huggingface.co/datasets/mks-logic/SPY), representing medical consultations and legal questions; the full released corpus has 4,491 medical and 4,197 legal examples (8,688 total), generated using Llama-3-70B and the Faker library. Fastino reports exact-match span-level metrics under the alias `fastino/gliner2-pii-v1`; the exact sample count and entity-generation seed used for the scores below are undisclosed.  
**Evaluation Benchmark Score:** Vendor-reported average F1 score (the harmonic mean of precision and recall): 0.477.

<details>
<summary><strong>Detailed Benchmark Comparison Table</strong></summary>

| Model | Legal precision | Legal recall | Legal F1 | Medical precision | Medical recall | Medical F1 | Average F1 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| fastino/gliner2-pii-v1 | .346 | .750 | .473 | .369 | .686 | .480 | .477 |
| nvidia/gliner-PII | .343 | .452 | .390 | .368 | .465 | .411 | .400 |
| urchade/gliner_multi_pii-v1 | .467 | .317 | .377 | .518 | .351 | .419 | .398 |
| openai/privacy-filter | .242 | .656 | .354 | .287 | .692 | .406 | .380 |

</details>

## Inference
**Acceleration Engine:** Other (PyTorch + GLiNER2; NVIDIA Dynamo Runtime 1.5.1 for request routing; custom FastAPI/Uvicorn gateway)  
**Test Hardware:** NVIDIA Lovelace (L40S); 1 GPU

## Additional Details
The vendor reports over-prediction of names, including confusion with common nouns, organizations, and products. Evaluation covers one benchmark and two domains; broader multilingual evaluation is ongoing. Synthetic training annotations have no human validation, and non-European locales and scripts remain unmeasured. The vendor recommends label-specific thresholds, dictionary filters, and domain calibration.

## Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/)

## Capabilities

- **Function Calling:** Not supported
- **Structured Output:** Not supported
- **Reasoning:** Not supported

## Prototype

```python
import json
from openai import OpenAI

client = OpenAI(base_url="https://integrate.api.nvidia.com/v1", api_key="$NVIDIA_API_KEY")
completion = client.chat.completions.create(
model="fastino/gliner2-pii",
messages=json.loads("[{\"role\":\"user\",\"content\":\"\"}]"),
extra_body={"labels": json.loads("\"\""), "threshold": 0.3},
)
print(json.loads(completion.choices[0].message.content))
```