bash
pip install transformers torch

python
from transformers import pipeline

Load the model and tokenizer
Model: https://huggingface.co/OpenMed/OpenMed-NER-ChemicalDetect-ModernClinical-149M
model_name = "OpenMed/OpenMed-NER-ChemicalDetect-ModernClinical-149M"

Create a pipeline
medical_ner_pipeline = pipeline(
    model=model_name,
    aggregation_strategy="simple"
)

Example usage
text = "The patient was administered acetylsalicylic acid for pain relief."
entities = medical_ner_pipeline(text)

print(entities)

token = entities[0]
print(text[token["start"] : token["end"]])

python
texts = [
    "The patient was administered acetylsalicylic acid for pain relief.",
    "Treatment with doxorubicin showed significant improvement in tumor regression.",
    "The compound benzylpenicillin demonstrated strong antimicrobial activity.",
    "Further studies are needed to understand the effects of methotrexate on rheumatoid arthritis.",
    "The synthesis of vancomycin remains a significant challenge in organic chemistry.",
]

Efficient batch processing with optimized batch size
Adjust batch_size based on your GPU memory (typically 8, 16, 32, or 64)
results = medical_ner_pipeline(texts, batch_size=8)

for i, entities in enumerate(results):
    print(f"Text {i+1} entities:")
    for entity in entities:
        print(f"  
{entity['word']} ({entity['entity_group']}): {entity['score']:.4f}")

python
from transformers.pipelines.pt_utils import KeyDataset
from datasets import Dataset
import pandas as pd

Load your data
Load a medical dataset from Hugging Face
from datasets import load_dataset

Load a public medical dataset (using a subset for testing)
medical_dataset = load_dataset("BI55/MedText", split="train[:100]")  
Load first 100 examples
data = pd.DataFrame({"text": medical_dataset["Completion"]})
dataset = Dataset.from_pandas(data)

Process with optimal batching for your hardware
batch_size = 16  
Tune this based on your GPU memory
results = []

for out in medical_ner_pipeline(KeyDataset(dataset, "text"), batch_size=batch_size):
    results.extend(out)

print(f"Processed {len(results)} texts with batching")

python
For limited GPU memory, use smaller batches
medical_ner_pipeline = pipeline(
    model=model_name,
    aggregation_strategy="simple",
    device=0  
Specify GPU device
)

Process with memory-efficient batching
for batch_start in range(0, len(texts), batch_size):
    batch = texts[batch_start:batch_start + batch_size]
    batch_results = medical_ner_pipeline(batch, batch_size=len(batch))
    results.extend(batch_results)

latex
@misc{panahi2025openmedneropensourcedomainadapted,
      title={OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets},
      author={Maziyar Panahi},
      year={2025},
      eprint={2508.01630},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.01630},
}