Commit
•
b261b5b
1
Parent(s):
e29972d
Update README.md
Browse files
README.md
CHANGED
|
@@ -118,55 +118,6 @@ print(tokenizer.decode(outputs[0]))
|
|
| 118 |
|
| 119 |
# Evaluation
|
| 120 |
|
| 121 |
-
<table>
|
| 122 |
-
<colgroup>
|
| 123 |
-
<col style="text-align: center;">
|
| 124 |
-
<col style="text-align: center;">
|
| 125 |
-
<col style="text-align: center;">
|
| 126 |
-
</colgroup>
|
| 127 |
-
<tr>
|
| 128 |
-
<th>Metrics</th>
|
| 129 |
-
<th>Llama3.1-8B</th>
|
| 130 |
-
<th style="background-color: rgba(80, 15, 213, 0.5);">Falcon3-7B-Base</th>
|
| 131 |
-
</tr>
|
| 132 |
-
<tr>
|
| 133 |
-
<td>MUSR</td>
|
| 134 |
-
<td>Row 1, Cell 2</td>
|
| 135 |
-
<td style="background-color: rgba(80, 15, 213, 0.5);">18.70</td>
|
| 136 |
-
</tr>
|
| 137 |
-
<tr>
|
| 138 |
-
<td>BBH</td>
|
| 139 |
-
<td>Row 2, Cell 2</td>
|
| 140 |
-
<td style="background-color: rgba(80, 15, 213, 0.5);">32.68</td>
|
| 141 |
-
</tr>
|
| 142 |
-
<tr>
|
| 143 |
-
<td>MMLU_PRO</td>
|
| 144 |
-
<td>Row 2, Cell 2</td>
|
| 145 |
-
<td style="background-color: rgba(80, 15, 213, 0.5);">32.43</td>
|
| 146 |
-
</tr>
|
| 147 |
-
<tr>
|
| 148 |
-
<td>IF_EVAL</td>
|
| 149 |
-
<td>Row 2, Cell 2</td>
|
| 150 |
-
<td style="background-color: rgba(80, 15, 213, 0.5);">34.27</td>
|
| 151 |
-
</tr>
|
| 152 |
-
<tr>
|
| 153 |
-
<th>GPQA</th>
|
| 154 |
-
<th>Row 2, Cell 2</th>
|
| 155 |
-
<th style="background-color: rgba(80, 15, 213, 0.5);">13.97</th>
|
| 156 |
-
</tr>
|
| 157 |
-
<tr>
|
| 158 |
-
<th>MATH</th>
|
| 159 |
-
<th>Row 2, Cell 2</th>
|
| 160 |
-
<th style="background-color: rgba(80, 15, 213, 0.5);">18.02</th>
|
| 161 |
-
</tr>
|
| 162 |
-
<tr>
|
| 163 |
-
<th>AVG</th>
|
| 164 |
-
<th>Row 2, Cell 2</th>
|
| 165 |
-
<th style="background-color: rgba(80, 15, 213, 0.5);">24.85</th>
|
| 166 |
-
</tr>
|
| 167 |
-
</table>
|
| 168 |
-
|
| 169 |
-
|
| 170 |
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
|
| 171 |
<colgroup>
|
| 172 |
<col style="width: 10%;">
|
|
@@ -174,11 +125,11 @@ print(tokenizer.decode(outputs[0]))
|
|
| 174 |
<col style="width: 7%;">
|
| 175 |
<col style="width: 7%;">
|
| 176 |
<col style="width: 7%;">
|
| 177 |
-
<col style="background-color: rgba(
|
| 178 |
<col style="width: 7%;">
|
| 179 |
<col style="width: 7%;">
|
| 180 |
<col style="width: 7%;">
|
| 181 |
-
<col style="background-color: rgba(
|
| 182 |
</colgroup>
|
| 183 |
<thead>
|
| 184 |
<tr>
|
|
|
|
| 118 |
|
| 119 |
# Evaluation
|
| 120 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
|
| 122 |
<colgroup>
|
| 123 |
<col style="width: 10%;">
|
|
|
|
| 125 |
<col style="width: 7%;">
|
| 126 |
<col style="width: 7%;">
|
| 127 |
<col style="width: 7%;">
|
| 128 |
+
<col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
|
| 129 |
<col style="width: 7%;">
|
| 130 |
<col style="width: 7%;">
|
| 131 |
<col style="width: 7%;">
|
| 132 |
+
<col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
|
| 133 |
</colgroup>
|
| 134 |
<thead>
|
| 135 |
<tr>
|