G

Gliner Large V2.5

Developed by gliner-community
GLiNER is a general-purpose named entity recognition (NER) model capable of identifying any type of entity, providing a practical alternative to traditional NER models.
Downloads 2,896
Release Time : 6/17/2024

Model Overview

GLiNER uses a bidirectional Transformer encoder (similar to BERT) to recognize any type of entity, addressing the limitation of traditional NER models that are restricted to predefined entity types, while also avoiding the high resource consumption of large language models (LLMs).

Model Features

General Entity Recognition
Capable of recognizing any type of entity, not limited to predefined entity types.
Resource Efficient
Lower resource consumption compared to large language models (LLMs), making it suitable for resource-constrained scenarios.
Multilingual Support
Supports named entity recognition in multiple languages.

Model Capabilities

Named Entity Recognition
Multilingual Entity Recognition
Custom Entity Type Recognition

Use Cases

Information Extraction
Person Recognition
Identify person names from text.
Example output: Cristiano Ronaldo dos Santos Aveiro => Person
Date Recognition
Identify date information from text.
Example output: February 5, 1985 => Date
Award Recognition
Identify award names from text.
Example output: Ballon d'Or => Award
Sports Analysis
Team Recognition
Identify team names from sports news.
Example output: Al-Nassr => Team
Event Recognition
Identify event names from sports news.
Example output: UEFA Champions League => Event
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase