---
title: EmergentMethods/gliner_large_news-v2.1
description: This model is a fine-tune of GLiNER aimed at improving accuracy across a broad range of topics, especially with respect to long-context news. DeBERTa, 435M parameters.
canonical_url: https://superlinked.com/models/emergentmethods-gliner_large_news-v2-1
last_updated: 2026-05-25
---

# EmergentMethods/gliner_large_news-v2.1

This model is a fine-tune of GLiNER aimed at improving accuracy across a broad range of topics, especially with respect to long-context news entity extraction.

Source: [EmergentMethods/gliner_large_news-v2.1 on HuggingFace](https://huggingface.co/EmergentMethods/gliner_large_news-v2.1)

## Overview

| Field | Value |
|-------|-------|
| Architecture | DeBERTa |
| Parameters | 435M |
| Tasks | Extract |
| Outputs | Entities |
| License | apache-2.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### CoNLL-2003

Domain: news · Task: ner · Language: en

Named entity recognition on Reuters newswire text

Corpus: 3,453 · Queries: 3,453

**Quality:** f1: 0.5527 · precision: 0.5704 · recall: 0.5361

[Reference](https://aclanthology.org/W03-0419/)