OpenMed-ZeroShot-NER-BloodCancer-Multi-209M

What it does

This zero-shot named-entity recognition model identifies cell line names in English clinical text, using labels supplied by the user at inference time. It reports an F1 score of 0.597 on the CLL corpus test set, with 209M parameters and a GLiNER backbone.

Best for

• Cell line mentions in clinical notes
• Hematology research text mining
• Cell line extraction from case reports

Note on the model card. Cell line name recognition in clinical text (CLL corpus, 2,156 documents; label CL = cell line). The model card's 'chronic lymphocytic leukemia' wording is a misreading of the corpus name; see the OpenMed paper, Table 1.

What it detects (1 labels)

Trained on the label below; you can pass any other label names at inference time.

• Cell line

Quality

Cell line name recognition in clinical text (CLL corpus, 2,156 documents; label CL = cell line). The model card's 'chronic lymphocytic leukemia' wording is a misreading of the corpus name; see the OpenMed paper, Table 1.

Use it

pip install gliner

from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-BloodCancer-Multi-209M")
print(model.predict_entities("Patient with type 2 diabetes and hypertension.", ["disease"]))

pip install "openmed[mlx]"

from openmed import analyze_text
from openmed.core.config import OpenMedConfig
result = analyze_text("Patient started imatinib in March.", model_name="OpenMed/OpenMed-ZeroShot-NER-BloodCancer-Multi-209M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)