Identifies species names in English scientific text with zero-shot labels
What it does
This model performs zero-shot named-entity recognition, finding species names in English scientific text, with user-supplied entity labels at inference. It reports an F1 score of 0.826 on the Species-800 benchmark, with 770M parameters and a GLiNER backbone.
Best for
- Species tagging in ecology studies
- Organism extraction from research papers
- Biocuration of taxonomic mentions
What it detects (1 labels)
Trained on the label below; you can pass any other label names at inference time.
- Species
Quality
| Benchmark | Species-800 · all models on this benchmark |
|---|---|
| F1 | 0.826 |
| Precision | 0.781 |
| Recall | 0.876 |
| Accuracy | 0.968 |
| Source | Reported by the authors (test_results.json in the repository) |
Species Entity Recognition - Species names from the Species-800 dataset
Use it
pip install gliner
from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-Organism-XLarge-770M")
print(model.predict_entities("Patient with type 2 diabetes and hypertension.", ["disease"]))All model information shown here is public and belongs to its authors: use and download it freely under each model’s license. The selection, organization, search design and presentation of this catalog are © 2026 Clinical Corpus. Please link to these pages rather than copy them.