Update README.md

added citation for olmes.

README.md

@@ -206,9 +206,8 @@ By implementing this innovative prevention strategy, we can significantly reduce
 
 **Evaluation Results:**
 <table>
-  
 <thead>
-    <caption style="text-align:center"><b>Comparison with different models over various benchmarks. Scores of AlpacaEval-2.0 and Arena-Hard are calculated with thinking=True</b></caption>
+    <caption style="text-align:center"><b>Comparison with different models over various benchmarks. Scores of AlpacaEval-2.0 and Arena-Hard are calculated with thinking=True</b><sup id="fnref1"><a href="#fn1">1</a></caption>
   <tr>
     <th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
     <th style="text-align:center; background-color: #001d6c; color: white;">ArenaHard</th>
@@ -222,53 +221,53 @@ By implementing this innovative prevention strategy, we can significantly reduce
     <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval+</th>
   <th style="text-align:center; background-color: #001d6c; color: white;">IFEval</th>
-  <th style="text-align:center; background-color: #001d6c; color: white;">Attaq</th>
+  <th style="text-align:center; background-color: #001d6c; color: white;">AttaQ</th>
   </tr></thead>
   <tbody>
 <tr>
-    <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-2B-Instruct</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">23.3</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">27.17</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">57.11</td> 
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">20.55</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.79</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">54.46</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">18.68</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.55</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.45</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">75.26</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">63.59</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">84.7</td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">23.3</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">27.17</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">57.11</td> 
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">20.55</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">59.79</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">54.46</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">18.68</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.55</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.45</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">75.26</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">63.59</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">84.7</td>
   </tr>
   <tr>
-      <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.2-2B-Instruct</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">24.86</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">34.51</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">57.18</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">20.56</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.8</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">52.27</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">21.12</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.02</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">80.13</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">73.39</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">61.55</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">83.23</td>
+      <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">24.86</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">34.51</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">57.18</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">20.56</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">59.8</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">52.27</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">21.12</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.02</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">80.13</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">73.39</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">61.55</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.23</td>
   </tr>
   <tr>
-      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-2B-Instruct</b></td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 28.86 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 43.45 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 55.88 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 18.4 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 58.97 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 52.51 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 35.98 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 72.48 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 80.51 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 75.68 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 65.8 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;">87.47</td>
+      <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"><b>Granite-3.3-2B-Instruct</b></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 28.86 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 43.45 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 55.88 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 18.4 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 58.97 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 52.51 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 35.98 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 72.48 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 80.51 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 75.68 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 65.8 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">87.47</td>
       </tr>
       
   <tr>
@@ -285,7 +284,6 @@ By implementing this innovative prevention strategy, we can significantly reduce
     <td style="text-align:center; background-color: #DAE8FF; color: black;">80.15</td>
     <td style="text-align:center; background-color: #DAE8FF; color: black;">79.10</td>
     <td style="text-align:center; background-color: #DAE8FF; color: black;">83.43</td>
-
   </tr>
            
   <tr>
@@ -335,7 +333,6 @@ By implementing this innovative prevention strategy, we can significantly reduce
     <td style="text-align:center; background-color: #DAE8FF; color: black;">59.10</td>
     <td style="text-align:center; background-color: #DAE8FF; color: black;">42.45</td>
   </tr>
-
   <tr>
     <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-8B-Instruct</td>
     <td style="text-align:center; background-color: #DAE8FF; color: black;">37.58</td>
@@ -352,7 +349,6 @@ By implementing this innovative prevention strategy, we can significantly reduce
     <td style="text-align:center; background-color: #DAE8FF; color: black;">85.73</td>
   </tr>
             
-
 <tr>
       <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.2-8B-Instruct</td>
     <td style="text-align:center; background-color: #DAE8FF; color: black;">55.25</td>
@@ -395,19 +391,19 @@ By implementing this innovative prevention strategy, we can significantly reduce
   </tr></thead>
   <tbody>
   <tr>
-    <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-2B-Instruct</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 0.89 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 35.07 </td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 0.89 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 35.07 </td>
   </tr>
   <tr>
-    <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.2-2B-Instruct</td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 0.89 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 35.54 </td>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 0.89 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 35.54 </td>
   </tr>
   <tr>
-      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-2B-Instruct</b></td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 3.28 </td>
-    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 58.09 </td>
+      <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"><b>Granite-3.3-2B-Instruct</b></td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 3.28 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 58.09 </td>
   </tr>
   <tr>
     <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-8B-Instruct</td>
@@ -425,9 +421,6 @@ By implementing this innovative prevention strategy, we can significantly reduce
     <td style="text-align:center; background-color: #DAE8FF; color: black;"> 69.02 </td>
   </tr>
     </tbody></table>
-    
-</tbody></table>
-
 <!-- <table>
   <caption><b>Thinking Ablation</b></caption>
 <thead>
@@ -532,6 +525,9 @@ Granite-3.3-2B-Instruct builds upon Granite-3.3-2B-Base, leveraging both permiss
 - 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
 - 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
 
+
+
+<p><a href="#fnref1" title="Jump back to reference">[1]</a> Evaluated using <a href="https://github.com/allenai/olmes">OLMES</a> (except the AttaQ scores)</p>
 <!-- ## Citation
 ```
 @misc{granite-models,