GLiNER2 is a unified model that performs named entity recognition, zero-shot classification, relation extraction, and structured data extraction using a single schema-based approach. It supports multiple languages and is available via the GLiNER2 library for easy integration into applications.
In the Other AI space, Gliner2 Multi takes a focused approach. It focuses on extracting structured information and classifying text using flexible, schema-driven prompts without task-specific fine-tuning. It is built as an open-source project for developers. Gliner2 Multi is open source under the Apache-2.0 license. The product ships for the command line and API.
fastino builds and maintains Gliner2 Multi, and the product first shipped in 2025. Development happens publicly on GitHub with 1.7k stars and 23 commits in the last 90 days. Key capabilities include Entity Extraction, Zero-Shot Classification, and Structured Data Extraction.
Latest indexed changes and source events
fastino/gliner2-multi-v1 verified by the PulseGate indexer
Other apps tracked under the same category.
