GLiNER PII Overview

Description:

This container houses GLiNER PII, which detects and classifies a broad range of Personally Identifiable Information (PII) and Protected Health Information (PHI) in structured and unstructured text.

GLiNER PII images carrying rc tags such as 1.0.0-rc1, are classified as Pre-Release candidates.

The container components are ready for commercial/non-commercial use.

License/Terms of Use:

GOVERNING TERMS: Use of the software is governed by the NVIDIA Software License Agreement and Product-Specific Terms for NVIDIA AI Products. Use of the associated model is governed by the NVIDIA Open Model License Agreement. Additional Information: Apache License, Version 2.0.

Deployment Geography:

Global

Release Date:

Build.NVIDIA.com 3/3/2026 via https://build.nvidia.com/nvidia/gliner-pii
Hugging Face 10/30/2025 via https://huggingface.co/nvidia/gliner-pii

Program Classes:

GLiNER PII Container includes the following model:

Deployment Details:

Deploying GLiNER-PII NIM from NGC

# Auth (generate key at https://org.ngc.nvidia.com/setup/api-keys)
export NGC_API_KEY=<your-key>
echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin

# Run
mkdir -p ~/.cache/nim
docker run -it --rm --name gliner-pii \
  --runtime=nvidia --gpus all --shm-size=16GB \
  -e NGC_API_KEY \
  -v ~/.cache/nim:/opt/nim/.cache \
  -u $(id -u) \
  -p 8000:8000 \
  nvcr.io/nim/nvidia/gliner-pii:1.0.0

# Test
curl http://localhost:8000/v1/health/ready
curl -X POST http://localhost:8000/v1/detect \
  -H "Content-Type: application/json" \
  -d '{"text": "Email john@example.com, SSN 123-45-6789", "labels": ["email", "ssn"], "threshold": 0.5}'

Requires: NGC API key, Docker, NVIDIA GPU. Model downloads on first startup (~1.5GB). Drop --runtime=nvidia --gpus all --shm-size for CPU-only mode.

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.

How GLiNER-PII's /v1/chat/completions differs from LLM NIMs:

GLiNER-PII is an NER model, not an LLM. Its /v1/chat/completions endpoint uses the OpenAI schema for compatibility but behaves differently:

• Only the last user message is read; its content is the text to scan
• LLM parameters (temperature, max_tokens, etc.) are ignored
• PII-specific parameters are supported: labels, threshold, chunk_length, overlap, flat_ner
• The assistant content is a JSON string with total_entities, entities (array of text, label, start, end, score), and tagged_text

Note: The native endpoint is POST /v1/detect. Use it directly when you don't need OpenAI-schema compatibility.

Example

curl -s http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
  "model": "nvidia/gliner-pii",
  "messages": [{"role": "user", "content": "Contact me at john@example.com or call (555) 123-4567"}],
  "labels": ["email", "phone_number"],
  "threshold": 0.5
}'

The response choices[0].message.content is a JSON string:

{
  "total_entities": 2,
  "entities": [
    {"text": "john@example.com", "label": "email", "start": 14, "end": 30, "score": 0.99},
    {"text": "(555) 123-4567", "label": "phone_number", "start": 39, "end": 53, "score": 0.97}
  ],
  "tagged_text": "Contact me at <email>john@example.com</email> or call <phone_number>(555) 123-4567</phone_number>"
}

Container Version(s):

gliner-pii:1.0.0-rc1

Security Common Vulnerabilities and Exposures (CVEs)

Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Get Help

NVIDIA Developer Community Forum

Get access to community knowledge base articles and support cases (https://forums.developer.nvidia.com/)

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. When downloaded or used in accordance with our terms of service, developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.

Get Help

Getting started with the NIM

Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NVIDIA NIM documentation for release documentation, deployment guides and more.

NVIDIA Developer Community Forum

For support, visit the NVIDIA Developer Community Forum.