metadata
license: mit
language:
- fr
base_model:
- distilbert/distilbert-base-uncased
Model Description
Named Entity Recognition (NER) model trained to identify specific entities in French text. The model is designed to recognize entities such as cities and train stations, which are useful for travel-related applications.
Model Architecture
The model is based on the AutoModelForTokenClassification architecture from the Hugging Face Transformers library. It uses a pre-trained transformer model fine-tuned on a custom dataset for NER tasks.
Training Data
The model was trained on a dataset of French train stations and cities. The data was preprocessed and converted into a format suitable for NER tasks. The training data includes various sentences with labeled entities.
Labels
The model recognizes the following labels:
O: Outside of a named entityB-START: Beginning of a start entityI-START: Inside of a start entityB-END: Beginning of an end entityI-END: Inside of an end entity
Usage
You can use this model with the Hugging Face transformers library.