gliner2-base-v1

by fastino

Unified NER, classification, and structured extraction in a single 205M CPU-efficient model

379Kdl/month

205Mparams

HuggingFace Use in Pipeline

Identifiers

Model ID

fastino/gliner2-base-v1

Feature URI

mixpeek://document_extractor@v1/fastino_gliner2_base_v1

Overview

GLiNER 2 unifies named entity recognition, text classification, and hierarchical structured data extraction into a single 205M-parameter model built on a pretrained transformer encoder. Unlike pipeline approaches that chain separate models or LLM-based extraction that requires GPU infrastructure, GLiNER 2 runs efficiently on CPU with an intuitive schema-based interface that accepts natural language type descriptions.

On Mixpeek, GLiNER 2 powers lightweight entity extraction pipelines that run alongside heavier models without competing for GPU resources. Its zero-shot generalization across domains (matching GPT-4o on CrossNER benchmarks) makes it ideal for extracting custom entities from transcripts, OCR output, and document text without fine-tuning.

Architecture

Pretrained transformer encoder with multi-task composition heads for NER, classification, and structured extraction. 205M parameters. Schema-driven interface supporting natural language entity type descriptions, nested and overlapping spans, and configurable single or multi-label classification.

Mixpeek SDK Integration

import { Mixpeek } from "mixpeek";

const mx = new Mixpeek({ apiKey: "API_KEY" });

await mx.collections.ingest({
  collection_id: "my-collection",
  source: { url: "https://example.com/document.pdf" },
  feature_extractors: [{
    name: "entity_extraction",
    version: "v1",
    params: {
      model_id: "fastino/gliner2-base-v1",
      entity_types: ["person", "organization", "product", "date"]
    }
  }]
});