GLiNER2 is a versatile model that unifies named entity recognition, relation extraction, text classification, and structured data extraction using a schema-based approach. It supports zero-shot and few-shot scenarios and can handle multiple tasks simultaneously. The model is distributed on Hugging Face and can be used with the dedicated GLiNER2 library.
Gliner2 Base sits in PulseGate's Other AI category. It focuses on performing flexible, schema-driven information extraction and classification from unstructured text without task-specific models. It is built as an open-source project for developers. The project is open source (Apache-2.0). Gliner2 Base is available on the command line and API.
Behind Gliner2 Base is fastino, and it first shipped in 2025. The project is developed in the open on GitHub with 1.7k stars and 27 commits in the last 90 days. Key capabilities include Named Entity Recognition, Text Classification, and Structured 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