---
title: knowledgator/gliner-bi-base-v2.0
description: GLiNER-bi-Encoder is a novel architecture for Named Entity Recognition (NER) that combines zero-shot flexibility with industrial-scale effic. null, null parameters.
canonical_url: https://superlinked.com/models/knowledgator-gliner-bi-base-v2-0
last_updated: 2026-06-08
---

# knowledgator/gliner-bi-base-v2.0

GLiNER-bi-Encoder is a novel architecture for Named Entity Recognition (NER) that combines zero-shot flexibility with industrial-scale efficiency. Unlike the original GLiNER, which uses joint encoding, the bi-encoder design decouples text and entity-type encoding, enabling the recognition of thou...

Source: [knowledgator/gliner-bi-base-v2.0 on HuggingFace](https://huggingface.co/knowledgator/gliner-bi-base-v2.0)
Base model: [jhu-clsp/ettin-encoder-32m](https://huggingface.co/jhu-clsp/ettin-encoder-32m)

## Overview

| Field | Value |
|-------|-------|
| Architecture | null |
| Parameters | null |
| Tasks | Extract |
| Outputs | Entities |
| Max sequence length | 1,024 tokens |
| 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: 0.6396 · precision: 0.5844 · recall: 0.7064

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