Update README.md
Browse files
README.md
CHANGED
|
@@ -85,9 +85,9 @@ The model was evaluated on the GSM8K benchmark.
|
|
| 85 |
<tr>
|
| 86 |
<td>GSM8K (strict-match)
|
| 87 |
</td>
|
| 88 |
-
<td>95.07
|
| 89 |
</td>
|
| 90 |
-
<td>94.80
|
| 91 |
</td>
|
| 92 |
<td>99.7%
|
| 93 |
</td>
|
|
@@ -95,9 +95,9 @@ The model was evaluated on the GSM8K benchmark.
|
|
| 95 |
<tr>
|
| 96 |
<td>GSM8K (flexible-extract)
|
| 97 |
</td>
|
| 98 |
-
<td>95.15
|
| 99 |
</td>
|
| 100 |
-
<td>94.77
|
| 101 |
</td>
|
| 102 |
<td>99.6%
|
| 103 |
</td>
|
|
|
|
| 85 |
<tr>
|
| 86 |
<td>GSM8K (strict-match)
|
| 87 |
</td>
|
| 88 |
+
<td>95.07
|
| 89 |
</td>
|
| 90 |
+
<td>94.80
|
| 91 |
</td>
|
| 92 |
<td>99.7%
|
| 93 |
</td>
|
|
|
|
| 95 |
<tr>
|
| 96 |
<td>GSM8K (flexible-extract)
|
| 97 |
</td>
|
| 98 |
+
<td>95.15
|
| 99 |
</td>
|
| 100 |
+
<td>94.77
|
| 101 |
</td>
|
| 102 |
<td>99.6%
|
| 103 |
</td>
|