slim.frikha
commited on
Commit
·
7aae4f3
1
Parent(s):
a64ebc0
docs(readme): update
Browse files
README.md
CHANGED
|
@@ -133,7 +133,7 @@ We report in the following table our internal pipeline benchmarks:
|
|
| 133 |
<td><b>79.1</b></td>
|
| 134 |
</tr>
|
| 135 |
<tr>
|
| 136 |
-
<td>
|
| 137 |
<td>79.8</td>
|
| 138 |
<td>72.7</td>
|
| 139 |
<td><b>80.9</b></td>
|
|
@@ -216,9 +216,9 @@ We report in the following table our internal pipeline benchmarks:
|
|
| 216 |
<tr>
|
| 217 |
<td>Tool use</td>
|
| 218 |
<td>BFCL AST (avg)</td>
|
| 219 |
-
<td>
|
| 220 |
-
<td>
|
| 221 |
-
<td>
|
| 222 |
</tr>
|
| 223 |
</tbody>
|
| 224 |
</table>
|
|
|
|
| 133 |
<td><b>79.1</b></td>
|
| 134 |
</tr>
|
| 135 |
<tr>
|
| 136 |
+
<td>GSM8K (8-shot, COT)</td>
|
| 137 |
<td>79.8</td>
|
| 138 |
<td>72.7</td>
|
| 139 |
<td><b>80.9</b></td>
|
|
|
|
| 216 |
<tr>
|
| 217 |
<td>Tool use</td>
|
| 218 |
<td>BFCL AST (avg)</td>
|
| 219 |
+
<td>90.6</td>
|
| 220 |
+
<td><b>91.4</b></td>
|
| 221 |
+
<td>72.3</td>
|
| 222 |
</tr>
|
| 223 |
</tbody>
|
| 224 |
</table>
|