Update README.md

README.md

@@ -2,68 +2,269 @@
 library_name: transformers
 license: mit
 base_model: almanach/moderncamembert-cv2-base
-tags:
-- generated_from_trainer
 metrics:
 - precision
 - recall
 - f1
 - accuracy
 model-index:
-- name: moderncamembert-cv2-frenchNER_4entities
+- name: Moderncamembert-3entities
   results: []
+datasets:
+- CATIE-AQ/frenchNER_3entities
+language:
+- fr
+widget:
+- text: "Le dévoilement du logo officiel des JO s'est déroulé le 21 octobre 2019 au Grand Rex. Ce nouvel emblème et cette nouvelle typographie ont été conçus par le designer Sylvain Boyer avec les agences Royalties & Ecobranding. Rond, il rassemble trois symboles : une médaille d'or, la flamme olympique et Marianne, symbolisée par un visage de femme mais privée de son bonnet phrygien caractéristique. La typographie dessinée fait référence à l'Art déco, mouvement artistique des années 1920, décennie pendant laquelle ont eu lieu pour la dernière fois les Jeux olympiques à Paris en 1924. Pour la première fois, ce logo sera unique pour les Jeux olympiques et les Jeux paralympiques."
+pipeline_tag: token-classification
+co2_eq_emissions: 22 
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Moderncamembert-3entities
 
-# moderncamembert-cv2-frenchNER_4entities
+## Model Description
 
-This model is a fine-tuned version of [almanach/moderncamembert-cv2-base](https://huggingface.co/almanach/moderncamembert-cv2-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1113
-- Precision: 0.9860
-- Recall: 0.9860
-- F1: 0.9860
-- Accuracy: 0.9860
+We present **Moderncamembert-3entities**, which is a [Moderncamembert-cv2-base](https://huggingface.co/almanach/moderncamembert-cv2-base) fine-tuned for the Name Entity Recognition task for the French language on four French NER datasets for 3 entities (LOC, PER, ORG).  
+All these datasets were concatenated and cleaned into a single dataset that we called [frenchNER_3entities](https://huggingface.co/datasets/CATIE-AQ/frenchNER_3entities).  
+This represents a total of over **420,264 rows, of which 346,071 are for training, 32,951 for validation and 41,242 for testing.**   
 
-## Model description
+## Evaluation results
 
-More information needed
+The evaluation was carried out using the [**evaluate**](https://pypi.org/project/evaluate/) python package.
 
-## Intended uses & limitations
 
-More information needed
+### frenchNER_3entities
 
-## Training and evaluation data
+For space reasons, we show only the F1 of the different models. You can see the full results below the table.
 
-More information needed
+<table>
+<thead>
+    <tr>
+      <th><br>Model</th>
+      <th><br>Parameters</th>
+      <th><br>Context</th>
+      <th><br>PER</th>
+      <th><br>LOC</th>
+      <th><br>ORG</th>
+    </tr>
+</thead>
+<tbody>
+    <tr>
+        <td rowspan="1"><br><a href="https://hf.co/Jean-Baptiste/camembert-ner">Jean-Baptiste/camembert-ner</a></td>
+        <td><br>110M</td>
+        <td><br>512 tokens</td>
+        <td><br>0.941</td>
+        <td><br>0.883</td>
+        <td><br>0.658</td>
+    </tr>
+      <tr>
+        <td rowspan="1"><br><a href="https://hf.co/cmarkea/distilcamembert-base-ner">cmarkea/distilcamembert-base-ner</a></td>
+        <td><br>67.5M</td>
+        <td><br>512 tokens</td>
+        <td><br>0.942</td>
+        <td><br>0.882</td>
+        <td><br>0.647</td>
+    </tr>
+    <tr>
+        <td rowspan="1"><br><a href="https://hf.co/CATIE-AQ/NERmembert-base-4entities">NERmembert-base-4entities</a></td>
+        <td><br>110M</td>
+        <td><br>512 tokens</td>
+        <td><br>0.951</td>
+        <td><br>0.894</td>
+        <td><br>0.671</td>
+    </tr>
+        <tr>
+        <td rowspan="1"><br><a href="https://hf.co/CATIE-AQ/NERmembert-large-4entities">NERmembert-large-4entities</a></td>
+        <td><br>336M</td>
+        <td><br>512 tokens</td>
+        <td><br>0.958</td>
+        <td><br>0.901</td>
+        <td><br>0.685</td>
+    </tr>
+    <tr>
+        <td rowspan="1"><br><a href="https://hf.co/CATIE-AQ/NERmembert-base-3entities">NERmembert-base-3entities</a></td>
+        <td><br>110M</td>
+        <td><br>512 tokens</td>
+        <td><br>0.966</td>
+        <td><br>0.940</td>
+        <td><br>0.876</td>
+    </tr>
+      <tr>
+        <td rowspan="1"><br><a href="https://hf.co/CATIE-AQ/NERmembert2-3entities">NERmembert2-3entities</a></td>
+        <td><br>111M</td>
+        <td><br>1024 tokens</td>
+        <td><br>0.967</td>
+        <td><br>0.942</td>
+        <td><br>0.875</td>
+    </tr>
+        <tr>
+        <td rowspan="1"><a href="https://huggingface.co/CATIE-AQ/NERmemberta-3entities">NERmemberta-3entities</a></td>
+        <td><br>111M</td>
+        <td><br>1024 tokens</td>
+        <td><br><b>0.970</b></td>
+        <td><br>0.943</td>
+        <td><br>0.881</td>
+      </tr>
+      <tr>
+        <td rowspan="1"><br>Moderncamembert_3entities (this model)</td>
+        <td><br>136M</td>
+        <td><br>8192 tokens</td>
+        <td><br>0.969</td>
+        <td><br>0.944</td>
+        <td><br>0.881</td>
+      </tr>
+      <tr>
+      <td rowspan="1"><br><a href="https://hf.co/CATIE-AQ/NERmembert-large-3entities">NERmembert-large-3entities</a></td>
+        <td><br>336M</td>
+        <td><br>512 tokens</td>
+        <td><br>0.969</td>
+        <td><br><b>0.947</b></td>
+        <td><br><b>0.890</b></td>
+    </tr>
+      </tr>
+</tbody>
+</table>
 
-## Training procedure
 
-### Training hyperparameters
+<details>
+<summary>Full results</summary>
+<code>
+{'LOC': {'precision': 0.9416666666666667,<br>
+  'recall': 0.9469231691557534,<br>
+  'f1': 0.9442876027128823,<br>
+  'number': 75061},<br>
+ 'O': {'precision': 0.9946557304890683,<br>
+  'recall': 0.9940143723727719,<br>
+  'f1': 0.9943349480099875,<br>
+  'number': 932066},<br>
+ 'ORG': {'precision': 0.886804772363032,<br>
+  'recall': 0.8749890187121145,<br>
+  'f1': 0.8808572734106688,<br>
+  'number': 34149},<br>
+ 'PER': {'precision': 0.965375959374459,<br>
+  'recall': 0.9725258115524137,<br>
+  'f1': 0.9689376958407905,<br>
+  'number': 86008},<br>
+ 'overall_precision': 0.9856336114058214,<br>
+ 'overall_recall': 0.9856336114058214,<br>
+ 'overall_f1': 0.9856336114058214,<br>
+ 'overall_accuracy': 0.9856336114058214}
+</code>
+ </details>
 
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 3
+## Usage
 
-### Training results
+```python
+from transformers import pipeline
 
-| Training Loss | Epoch | Step   | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0274        | 1.0   | 43650  | 0.0892          | 0.9835    | 0.9835 | 0.9835 | 0.9835   |
-| 0.0119        | 2.0   | 87300  | 0.0825          | 0.9858    | 0.9858 | 0.9858 | 0.9858   |
-| 0.0038        | 3.0   | 130950 | 0.1113          | 0.9860    | 0.9860 | 0.9860 | 0.9860   |
+ner = pipeline('token-classification', model='CATIE-AQ/Moderncamembert-3entities', tokenizer='CATIE-AQ/Moderncamembert-3entities', aggregation_strategy="simple")
 
+result = ner(
+"Le dévoilement du logo officiel des JO s'est déroulé le 21 octobre 2019 au Grand Rex. Ce nouvel emblème et cette nouvelle typographie ont été conçus par le designer Sylvain Boyer avec les agences Royalties & Ecobranding. Rond, il rassemble trois symboles : une médaille d'or, la flamme olympique et Marianne, symbolisée par un visage de femme mais privée de son bonnet phrygien caractéristique. La typographie dessinée fait référence à l'Art déco, mouvement artistique des années 1920, décennie pendant laquelle ont eu lieu pour la dernière fois les Jeux olympiques à Paris en 1924. Pour la première fois, ce logo sera unique pour les Jeux olympiques et les Jeux paralympiques."
+)
 
-### Framework versions
+print(result)
+```
 
-- Transformers 4.51.3
-- Pytorch 2.6.0+cu124
-- Datasets 2.16.0
-- Tokenizers 0.21.0
+## Environmental Impact
+
+*Carbon emissions were estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.*
+
+- **Hardware Type:** A100 PCIe 40/80GB
+- **Hours used:** 2h48min
+- **Cloud Provider:** Private Infrastructure
+- **Carbon Efficiency (kg/kWh):** 0.032 (estimated from [electricitymaps](https://app.electricitymaps.com/zone/FR) for the day of April 15, 2025.)
+- **Carbon Emitted** *(Power consumption x Time x Carbon produced based on location of power grid)*: 0.022 kg eq. CO2
+
+
+
+
+## Citations
+
+### Moderncamembert-3entities
+```
+@misc {NERmemberta2024,
+    author       = { {BOURDOIS, Loïck} },  
+    organization = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+	title        = { Moderncamembert-3entities},
+	year         = 2025,
+	url          = { https://huggingface.co/CATIE-AQ/Moderncamembert-3entities },
+	doi          = { 10.57967/hf/3640 },
+	publisher    = { Hugging Face }
+}
+```
+
+### Moderncamembert-cv2-base
+```
+@misc{antoun2025modernbertdebertav3examiningarchitecture,
+      title={ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance}, 
+      author={Wissam Antoun and Benoît Sagot and Djamé Seddah},
+      year={2025},
+      eprint={2504.08716},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2504.08716}, 
+}
+```
+
+### NERmemBERTa-3entities
+```
+@misc {NERmemberta2024,
+    author       = { {BOURDOIS, Loïck} },  
+    organization = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+	title        = { NERmemberta-3entities},
+	year         = 2024,
+	url          = { https://huggingface.co/CATIE-AQ/NERmemberta-3entities },
+	doi          = { 10.57967/hf/3640 },
+	publisher    = { Hugging Face }
+}
+```
+### CamemBERT 2.0
+```
+@misc{antoun2024camembert20smarterfrench,
+      title={CamemBERT 2.0: A Smarter French Language Model Aged to Perfection}, 
+      author={Wissam Antoun and Francis Kulumba and Rian Touchent and Éric de la Clergerie and Benoît Sagot and Djamé Seddah},
+      year={2024},
+      eprint={2411.08868},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2411.08868}, 
+}
+```
+### NERmemBERT
+```
+@misc {NERmembert2024,
+    author       = { {BOURDOIS, Loïck} },  
+    organization = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+	title        = { NERmembert-base-3entities },
+	year         = 2024,
+	url          = { https://huggingface.co/CATIE-AQ/NERmembert-base-3entities },
+	doi          = { 10.57967/hf/1752 },
+	publisher    = { Hugging Face }
+}
+```
+
+### CamemBERT
+```
+@inproceedings{martin2020camembert,  
+  title={CamemBERT: a Tasty French Language Model},  
+  author={Martin, Louis and Muller, Benjamin and Su{\'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {\'E}ric Villemonte and Seddah, Djam{\'e} and Sagot, Beno{\^\i}t},  
+  booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},  
+  year={2020}}
+```
+
+### frenchNER_3entities
+```
+@misc {frenchNER2024,  
+    author       = { {BOURDOIS, Loïck} },  
+    organization  = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+    title        = { frenchNER_4entities },  
+    year         = 2024,  
+    url          = { https://huggingface.co/CATIE-AQ/frenchNER_3entities },  
+    doi          = { 10.57967/hf/1751 },  
+    publisher    = { Hugging Face }  
+}
+```
+
+## License
+MIT