# urchade/GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)

Repository: https://github.com/urchade/GLiNER
Canonical: https://ross.abutalabs.com/products/gliner
Homepage: https://urchade.github.io/GLiNER
Language: Python
License: Apache-2.0
License Family: permissive
Topics: information-extraction, large-language-models, named-entity-recognition, natural-language-processing, prompt-tuning
Last push: 2026-08-10T09:21:43+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 82, longevity 73
- inputs: {"age_days": 1023, "days_push": 23, "days_rel": 40, "gap_med": 36.5, "n_releases_24m": 17}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3574, forks 299 (observed 2026-08-28T04:08:10.727332+00:00)

## What it is
GLiNER is a Python framework for training and deploying lightweight, zero-shot Named Entity Recognition models that can extract arbitrary entity types from text without labeled data. It also supports streaming NER, joint entity and relation extraction, and multi-task token classification, running efficiently on CPUs and consumer hardware.

## Use cases
- extract named entities from text without training data
- detect PII in documents
- perform zero-shot NER with custom entity types
- extract entities and relations jointly
- run NER on CPU without a GPU
- stream entity recognition over incremental text
- fine-tune a small NER model on my own labels

## When to choose
- you need flexible entity types without training a task-specific model
- you want LLM-like extraction flexibility at a fraction of the cost and size
- you need to deploy NER on CPU or edge hardware with ONNX/INT8 support

## When to avoid
- you need a fixed set of predefined entity types with maximum accuracy from a classic NER model
- you need full generative LLM capabilities beyond entity extraction
- you are not working in the Python/PyTorch ecosystem

## Facets
- artifact type: library
- maturity: active
- function: nlp, machine-learning, llm-inference
- domain: machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: named-entity-recognition, zero-shot, information-extraction, relation-extraction, pii-detection, transformers, onnx, token-classification, natural-language-processing, gpu

## Member repositories
- urchade/GLiNER (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:10.727332+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:34:04.741271+00:00, confidence not recorded.
  - readme: https://github.com/urchade/GLiNER (fetched 2026-08-28T04:08:10.727332+00:00, sha 8de9d5f56d3f)
  - homepage: https://urchade.github.io/GLiNER (fetched 2026-08-29T09:27:38.494036+00:00, sha baf078eb9956)
  - registry_pypi: https://pypi.org/pypi/gliner/json (fetched 2026-08-29T09:27:38.496792+00:00, sha bd001a5e73f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.