Update README.md

README.md

@@ -17,7 +17,7 @@ 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."
 library_name: transformers
 pipeline_tag: token-classification
-co2_eq_emissions: 35
+co2_eq_emissions: 90
 ---
 
 
@@ -33,7 +33,7 @@ Our methodology is described in a blog post available in [English](https://blog.
 
 ## Dataset
 
-The dataset used is [frenchNER_3entities](https://huggingface.co/datasets/CATIE-AQ/frenchNER_3entities), which represents ~420k sentences labeled in 4 categories :
+The dataset used is [frenchNER_3entities](https://huggingface.co/datasets/CATIE-AQ/frenchNER_3entities), which represents ~420k sentences labeled in 4 categories:
 | Label | Examples                                                   |
 |:------|:-----------------------------------------------------------|
 | PER   | "La Bruyère", "Gaspard de Coligny", "Wittgenstein"         |
@@ -529,7 +529,7 @@ For space reasons, we show only the F1 of the different models. You can see the
     </tr>
 </tbody>
 </table>
-</details
+</details>
 
   
 ### multinerd
@@ -771,9 +771,9 @@ For space reasons, we show only the F1 of the different models. You can see the
 <tbody>
     <tr>
         <td rowspan="1"><br><a href="https://hf.co/Jean-Baptiste/camembert-ner">Jean-Baptiste/camembert-ner</a></td>
-        <td><br>0.986</td>
-        <td><br>0.966</td>
-        <td><br>0.938</td>
+        <td><br><b>0.986</b></td>
+        <td><br><b>0.966</b></td>
+        <td><br><b>0.938</b></td>
     </tr>
       <tr>
         <td rowspan="1"><br><a href="https://hf.co/cmarkea/distilcamembert-base-ner">cmarkea/distilcamembert-base-ner</a></td>
@@ -789,9 +789,9 @@ For space reasons, we show only the F1 of the different models. You can see the
     </tr>
       <tr>
       <td rowspan="1"><br>NERmembert-large-3entities (this model)</td>
-        <td><br><b>0.972</b></td>
-        <td><br><b>0.950</b></td>
-        <td><br><b>0.893</b></td>
+        <td><br>0.972</td>
+        <td><br>0.950</td>
+        <td><br>0.893</td>
     </tr>
       <tr>
         <td rowspan="1"><br><a href="https://hf.co/CATIE-AQ/NERmembert-base-4entities">NERmembert-base-4entities</a></td>
@@ -843,11 +843,11 @@ For space reasons, we show only the F1 of the different models. You can see the
     </tr>
     <tr>
         <td>F1</td>
-        <td><br>0.986</td>
-        <td><br>0.966</td>
-        <td><br>0.938</td>
-        <td><br>0.982</td>
-        <td><br>0.980</td>
+        <td><br><b></b>0.986</b></td>
+        <td><br><b>0.966</b></td>
+        <td><br><b>0.938</b></td>
+        <td><br><b>0.982</b></td>
+        <td><br><b>0.980</b></td>
     </tr>
       <tr>
         <td rowspan="3"><br><a href="https://hf.co/cmarkea/distilcamembert-base-ner">cmarkea/distilcamembert-base-ner</a></td>
@@ -918,11 +918,11 @@ For space reasons, we show only the F1 of the different models. You can see the
     </tr>
     <tr>
         <td>F1</td>
-        <td><br><b>0.972</b></td>
-        <td><br><b>0.950</b></td>
-        <td><br><b>0.893</b></td>
-        <td><br><b>0.996</b></td>
-        <td><br><b>0.990</b></td>
+        <td><br>0.972</td>
+        <td><br>0.950</td>
+        <td><br>0.893</td>
+        <td><br>0.996</td>
+        <td><br>0.990</td>
     </tr>
       <tr>
         <td rowspan="3"><br><a href="https://hf.co/CATIE-AQ/NERmembert-base-4entities">NERmembert-base-4entities</a></td>
@@ -1050,7 +1050,7 @@ For space reasons, we show only the F1 of the different models. You can see the
       <tr>
         <td rowspan="3"><br><a href="https://hf.co/Jean-Baptiste/camembert-ner">Jean-Baptiste/camembert-ner</a></td>
         <td><br>Precision</td>
-        <td><br>0.862></td>
+        <td><br>0.862</td>
         <td><br>0.700</td>
         <td><br>0.864</td>
         <td><br>0.867</td>
@@ -1262,10 +1262,10 @@ The following hyperparameters were used during training:
 *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:** 1h45min
+- **Hours used:** 4h31min
 - **Cloud Provider:** Private Infrastructure
-- **Carbon Efficiency (kg/kWh):** 0.079 (estimated from [electricitymaps](https://app.electricitymaps.com/zone/FR) for the day of December 15, 2023.)
-- **Carbon Emitted** *(Power consumption x Time x Carbon produced based on location of power grid)*: 0.035 kg eq. CO2
+- **Carbon Efficiency (kg/kWh):** 0.077 (estimated from [electricitymaps](https://app.electricitymaps.com/zone/FR) for the day of January 12, 2024.)
+- **Carbon Emitted** *(Power consumption x Time x Carbon produced based on location of power grid)*: 0.009 kg eq. CO2