GLiNER2 is a large transformer model that unifies named entity recognition, relation extraction, text classification, and structured data extraction under a single schema-based framework. Users define entity types or classes at inference time. It supports multiple languages and is distributed with a dedicated GLiNER2 Python library.
Gliner2 Large sits in PulseGate's Classification & entity recognition category. It focuses on performing flexible, schema-driven information extraction without task-specific fine-tuning. Gliner2 Large is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the command line and API.
It is developed by fastino, and it first shipped in 2025. The project is developed in the open on GitHub with 1.7k stars and 34 commits in the last 90 days. Among its 3 catalogued features are Named Entity Recognition, Text Classification, and Schema-based Extraction.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do