---
title: knowledgator/gliclass-base-v1.0
description: This is an efficient zero-shot classifier inspired by GLiNER work. It demonstrates the same performance as a cross-encoder while being more . DeBERTa, 186M parameters.
canonical_url: https://superlinked.com/models/knowledgator-gliclass-base-v1-0
last_updated: 2026-08-24
---

# knowledgator/gliclass-base-v1.0

This is an efficient zero-shot classifier inspired by GLiNER work. It demonstrates the same performance as a cross-encoder while being more compute-efficient because classification is done at a single forward path.

Source: [knowledgator/gliclass-base-v1.0 on HuggingFace](https://huggingface.co/knowledgator/gliclass-base-v1.0)

## Overview

| Field | Value |
|-------|-------|
| Architecture | DeBERTa |
| Parameters | 186M |
| Tasks | Extract |
| Outputs | Class Labels |
| Max sequence length | 512 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### AG News

Domain: news · Task: classification · Language: en

Topic classification of news articles into world, sports, business, and sci/tech categories

Corpus: 7,600 · Queries: 7,600

**Quality:** accuracy: 0.7188

[Reference](https://arxiv.org/abs/1509.01626)

### medical_questions_pairs

Domain: medical · Task: classification · Language: en

Classify whether two medical questions ask the same thing (question-pair similarity)

Corpus: 3,048 · Queries: 3,048

**Quality:** accuracy: 0.4895

[Reference](https://huggingface.co/datasets/medical_questions_pairs)