---
title: jackboyla/glirel-large-v0
description: GLiREL is a Relation Extraction model capable of classifying unseen relations given the entities within a text. This builds upon the excelen. DeBERTa, 435M parameters.
canonical_url: https://superlinked.com/models/jackboyla-glirel-large-v0
last_updated: 2026-05-25
---

# jackboyla/glirel-large-v0

GLiREL is a Relation Extraction model capable of classifying unseen relations given the entities within a text. This builds upon the excelent work done by Urchade Zaratiana, Nadi Tomeh, Pierre Holat, Thierry Charnois on the GLiNER library which enables efficient zero-shot Named Entity Recognition.

Source: [jackboyla/glirel-large-v0 on HuggingFace](https://huggingface.co/jackboyla/glirel-large-v0)

## Overview

| Field | Value |
|-------|-------|
| Architecture | DeBERTa |
| Parameters | 435M |
| Tasks | Extract |
| Outputs | Relations |
| Inputs | text |

## Benchmarks

### FewRel

Domain: general · Task: re · Language: en

Few-shot relation extraction from Wikipedia sentences

Corpus: 70,000 · Queries: 70,000

**Quality:** f1: 0.2639 · precision: 0.2397 · recall: 0.2934

[Reference](https://aclanthology.org/D18-1514/)