neuralmagic
/

Meta-Llama-3.1-405B-Instruct-FP8-dynamic

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

Lin-K76 commited on Jul 24

Commit

6c0fcdd

•

1 Parent(s): e32ba06

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -159,7 +159,7 @@ Certain benchmarks for the full precision model are still being acquired. Averag
    </td>
    <td>*
    </td>
-   <td>88.34
    </td>
    <td>*
    </td>
@@ -221,7 +221,7 @@ Certain benchmarks for the full precision model are still being acquired. Averag
    </td>
    <td><strong>82.38</strong>
    </td>
-   <td><strong>98.95%</strong>
    </td>
   </tr>
 </table>

    </td>
    <td>*
    </td>
+   <td>86.17
    </td>
    <td>*
    </td>
    </td>
    <td><strong>82.38</strong>
    </td>
+   <td><strong>99.72%</strong>
    </td>
   </tr>
 </table>