README.md

---
license: apache-2.0
datasets:
- TypicaAI/MedicalNER_Fr
language:
- fr
metrics:
- f1
base_model:
- almanach/camembert-bio-base
library_name: transformers
tags:
- educational
- healthcare-ner
- french-ner
- nlp-book
- medical
extra_gated_prompt: "You agree to not use the model for medical decisions nor for production use."
extra_gated_fields:
  I want to use this model for:
    type: select
    options: 
      - Education
      - Research
      - label: Other
        value: other
  I agree to use this model for non-commercial use ONLY: checkbox
---
# French Healthcare NER Model (Educational Version)

This French Healthcare NER model is part of the healthcare NLP case study featured in the book *[Natural Language Processing on Oracle Cloud Infrastructure: Building Transformer-Based NLP Solutions Using Oracle AI and Hugging Face](https://a.co/d/h0xL4lo).* Dive into Chapter 6 for a comprehensive, step-by-step guide on building this model.

## 📚 Purpose and Scope

This model is designed to complement Chapter 6 of the book, allowing readers to:

- **Explore the Model**: Experiment with the healthcare NLP model built in the book without needing to train one from scratch.  
- **Recreate the Case Study**: Follow along with the step-by-step implementation detailed in Chapter 6.  
- **Understand Key Concepts**: Learn how to fine-tune and apply a healthcare NER model to French-language data.  

This pre-built model simplifies the learning process and enables hands-on practice directly aligned with the book's content.

## ⚠️ Usage Restrictions

This is a demo model provided for educational purposes. It was trained on a limited dataset and is not intended for production use, clinical decision-making, or real-world medical applications.

- Educational and research purposes only
- Not licensed for commercial deployment
- Not for production use
- Not for medical decisions

## 🎓 Book Reference

This model is built as described in Chapter 6 of the book *Natural Language Processing on Oracle Cloud Infrastructure*. The book covers the entire NLP solution lifecycle—including data preparation, model fine-tuning, deployment, and monitoring. Chapter 6 specifically focuses on:

- Fine-tuning a pretrained model from Hugging Face Hub for healthcare Named Entity Recognition (NER)  
- Training the model using OCI’s Data Science service and Hugging Face Transformers libraries 
- Performance evaluation and best practices for robust and cost-effective NLP models  

For more details, you can explore the book and Chapter 6 on the following platforms:  
- **Full Book on Springer**: [View Here](https://link.springer.com/book/10.1007/979-8-8688-1073-2)  
- **Chapter 6 on Springer**: [Read Chapter 6](https://link.springer.com/chapter/10.1007/979-8-8688-1073-2_6)  
- **Amazon**: [Learn More](https://a.co/d/3jDIQki)

## Citation

<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
If you use this model, please cite the following:

```bibtex
@Inbook{Assoudi2024,
author="Assoudi, Hicham",
title="Model Fine-Tuning",
bookTitle="Natural Language Processing on Oracle Cloud Infrastructure: Building Transformer-Based NLP Solutions Using Oracle AI and Hugging Face",
year="2024",
publisher="Apress",
address="Berkeley, CA",
pages="249--319",
abstract="This chapter focuses on the process of fine-tuning a pretrained model for healthcare Named Entity Recognition (NER). This chapter provides an in-depth exploration of training the healthcare NER model using OCI's Data Science platform and Hugging Face tools. It covers the fine-tuning process, performance evaluation, and best practices that contribute to creating robust and cost-effective NLP models.",
isbn="979-8-8688-1073-2",
doi="10.1007/979-8-8688-1073-2_6",
url="https://doi.org/10.1007/979-8-8688-1073-2_6"
}
```

## 📞 Connect and Contact

Stay updated on my latest models and projects:  
👉 **[Follow me on Hugging Face](https://huggingface.co/hassoudi)**  

For inquiries or professional communication, feel free to reach out:  
📧 **Email**: [[email protected]](mailto:[email protected])