README.md

---
license: mit
language:
- en
tags:
- bio
- infrastructure
- funding
- natural language processing
- BERT
---

# Biodata Resource Inventory

This repository holds the fine-tuned models used in the biodata resource inventory conducted in 2022 by the
[Global Biodata Coalition](https://globalbiodata.org/) in collaboration with [Chan Zuckerberg Initiative](https://chanzuckerberg.com/).

## Repository Overview

The fine-tuned models for both the article classification and NER tasks are present, and each has an associated modelcard.

```sh
.
├── article_classifier.pt                  # Article classification model checkpoint
├── article_classifier_modelcard.md        # Model card for article classification model
├── name_entity_recognition.pt             # NER model checkpoint
└── name_entity_recognition_modelcard.pt   # Modelcard for NER model
```

## Associated Code

The associated code, data, and documentation for this project can be found on [GitHub](https://github.com/globalbiodata/inventory_2022/tree/inventory_2022_dev).