Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,85 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- fr
|
| 5 |
+
tags:
|
| 6 |
+
- Objectifs de développement durable (ODD)
|
| 7 |
+
- SDG
|
| 8 |
+
- FlauBERT Large
|
| 9 |
+
- BERT
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
# ilovebots/bert-sdg-french
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
Ce modèle permet de classer les textes en fonction des objectifs de développement durable (ODD) des Nations Unies.
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
<img src="https://www.ulaval.ca/sites/default/files/DD/ODD/Tableau%20ODD.jpg" alt="image" width="600"/>
|
| 20 |
+
|
| 21 |
+
Source: [https://www.un.org/development/desa/disabilities/about-us/sustainable-development-goals-sdgs-and-disability.html](https://www.un.org/development/desa/disabilities/about-us/sustainable-development-goals-sdgs-and-disability.html)
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
## Détails du modèle
|
| 25 |
+
|
| 26 |
+
### Description du modèle
|
| 27 |
+
|
| 28 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 29 |
+
|
| 30 |
+
Ce modèle de classification de texte a été développé en fine-tuning le modèle pré-entraîné dbmdz/bert-base-french-europeana-cased.
|
| 31 |
+
Les données d'entraînement de ce modèle affiné proviennent de l'ensemble de données communautaires OSDG (OSDG-CD) accessible au public à l'adresse https://zenodo.org/record/5550238#.ZBulfcJByF4.
|
| 32 |
+
Ce modèle a été réalisé dans le cadre d'une recherche universitaire à l'[Université Laval](https://www.ulaval.ca/developpement-durable/objectifs-de-developpement-durable-de-lonu).<br>
|
| 33 |
+
L'objectif était de créer un modèle de classification de texte SDG basé sur transformers en français.<br>
|
| 34 |
+
Les principaux détails du modèle sont mis en évidence ci-dessous :
|
| 35 |
+
|
| 36 |
+
- **Model type:** Text classification
|
| 37 |
+
- **Language(s) (NLP):** French
|
| 38 |
+
- **License:** mit
|
| 39 |
+
- **Finetuned from model :** flaubert/flaubert_large_cased
|
| 40 |
+
|
| 41 |
+
### Model Sources
|
| 42 |
+
<!-- Provide the basic links for the model. -->
|
| 43 |
+
- **Repository:** https://huggingface.co/ilovebots/Flaubert_large_SDG_French
|
| 44 |
+
|
| 45 |
+
## How to Get Started with the Model
|
| 46 |
+
|
| 47 |
+
Utilisez le code ci-dessous pour commencer à utiliser le modèle.
|
| 48 |
+
```python
|
| 49 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 50 |
+
tokenizer = AutoTokenizer.from_pretrained("ilovebots/Flaubert_large_SDG_French")
|
| 51 |
+
model = AutoModelForSequenceClassification.from_pretrained("ilovebots/Flaubert_large_SDG_French")
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
## Training Data
|
| 56 |
+
|
| 57 |
+
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 58 |
+
La base disponible dans https://zenodo.org/record/5550238#.ZBulfcJByF4 a été enrichie des objectifs de développement durable des Nations Unies et traduite en en français.
|
| 59 |
+
|
| 60 |
+
## Training Hyperparameters
|
| 61 |
+
|
| 62 |
+
- Num_epoch = 4
|
| 63 |
+
- Learning rate = 2e-5
|
| 64 |
+
- Epsilon = 1e-8
|
| 65 |
+
- Optimizer = AdamW
|
| 66 |
+
- Batch size = 32
|
| 67 |
+
- Seed random = 42
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
## Evaluation
|
| 71 |
+
|
| 72 |
+
#### Metrics
|
| 73 |
+
|
| 74 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 75 |
+
- Accuracy = 0.84
|
| 76 |
+
|
| 77 |
+
<img src="https://raw.githubusercontent.com/I-Love-Bots/public/main/BertFinetuning.png" alt="image" width="600"/>
|
| 78 |
+
|
| 79 |
+
## Citation
|
| 80 |
+
Martinez, D.F. (2023). SDG classification with BERT. https://huggingface.co/ilovebots/Flaubert_large_SDG_French
|
| 81 |
+
|
| 82 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
<!--## Model Card Contact -->
|