GLiNER NER Testbed

Models Available:

• GLiNER Medium v2.1: The original GLiNER medium model
• GLiNER Multi PII: Fine-tuned for detecting personally identifiable information across multiple languages
• NuNER Zero: A specialized token-based NER model

Features:

• Select different models
• Select examples based on different use cases
• Toggle nested entity recognition
• Entity merging is currently enabled for NuNER Zero only

About GLiNER:

GLiNER is a state-of-the-art Named Entity Recognition (NER) system that leverages a BERT-like bidirectional transformer encoder to identify a wide range of entity types in text. Unlike conventional NER models that are restricted to fixed entity categories, GLiNER supports flexible, zero-shot extraction, making it ideal for diverse real-world applications. It also provides a resource-efficient alternative to large language models (LLMs) for scenarios where cost and speed are critical. Distributed under the Apache 2.0 license, GLiNER is commercially friendly and readily deployable.

Useful Links

• Model: gliner_medium-v2.1
• All GLiNER Models: Hugging Face GLiNER Models
• Research Paper: arXiv:2311.08526
• Repository: GitHub - GLiNER