108M BERT token classifier
Captured config identifies BertForTokenClassification and Safetensors metadata reports 107721987 parameters.
Open Source Model Profile · OpenMed
OpenMed-NER-PharmaDetect-BioPatient-108M
OpenMed-NER-PharmaDetect-BioPatient-108M is a 108M-parameter BERT token-classification fine-tune from OpenMed. Its model card documents chemical entity recognition on BC5CDR with B-CHEM and I-CHEM labels.
- Publisher
- OpenMed
- Task
- token-classification
- Model type
- bert
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
OpenMed-NER-PharmaDetect-BioPatient-108M is published by OpenMed as a BERT-based token-classification model. Safetensors metadata reports 107721987 parameters, and the captured configuration identifies BertForTokenClassification. According to the model card, it is a fine-tuned transformer for chemical entity recognition on the BC5CDR dataset.
Recorded capabilities
BC5CDR chemical recognition
According to the model card, the model targets chemical entity recognition on the BC5CDR dataset with B-CHEM and I-CHEM labels.
Publisher-reported metrics
The model card reports F1 0.9583, precision 0.9511, recall 0.9656, and accuracy 0.9857, with a sixth-place spot in its BC5CDR_CHEM comparison table.
Transformers pipeline use
The model card documents Hugging Face Transformers pipeline loading and lists Bio_Discharge_Summary_BERT as the base architecture.
Use cases in the source record
- Chemical entity extraction from clinical texts and research papers that uses the documented B-CHEM and I-CHEM labels.
- Biomedical text workflows such as medication extraction, drug-interaction detection, and literature mining described in the model card.
Limitations and unknowns
- No context-window value was extracted from this record.
- Performance figures are publisher-reported model-card values and have not been independently verified by Ethen.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Marketing-style superlatives in the model card are publisher descriptions and have not been independently verified by Ethen.
Source and provenance
Source: OpenMed/OpenMed-NER-PharmaDetect-BioPatient-108M
Captured: Unknown. Processed: 2026-09-07T19:35:50.713694+00:00.
🧬 OpenMed-NER-PharmaDetect-BioPatient-108M Specialized model for Chemical Entity Recognition - Chemical entities from the BC5CDR dataset 📋 Model Overview This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for chemical entity recognition - chemical entities from the bc5cdr dataset. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as drug interaction detection , medication extraction from patient records , adverse event monitoring , literature mining for drug d…
F001F002F003F004F005F006F007F009F010F011F012F014F015F023