OpenMed/OpenMed NER GenomeDetect ModernMed 149M

What it is

A token-classification model designed to detect named entities related to genomes within modern medical literature, aiding researchers and practitioners in extracting relevant genomic information.

This model is uniquely tailored for genome detection in medical texts, offering high precision and recall specifically for this domain.

When it fits — and when it doesn’t

Known weaknesses

Each one links to the public issue, changelog or docs page it came from, where we have one.

1. 01

   Limited language support beyond English medical literature

   Model training and testing have been primarily focused on English texts, with no documented support for other languages.

2. 02

   Performance degradation on large-scale datasets

   The model may experience significant slowdowns when processing extensive medical literature due to its specialized nature and complexity.

3. 03

   Dependency on transformers library can lead to version conflicts

   Integration with the latest versions of the transformers library may introduce incompatibilities, requiring frequent updates or patches.

What it does well

• Specialized for genome detection in medical texts

• High accuracy in named entity recognition tasks

• Based on the transformers library

Pricing

Free tier

YesOpen source — free to use

Paid from

$0

Model

Flat rate

Enterprise plan

No

Pricing not independently confirmed — check the vendor’s page.