RedHatAI
/

Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8

Image-Text-to-Text

compressed-tensors

8-bit precision

Model card Files Files and versions

alexmarques commited on Apr 15, 2025

Commit

1d6d7c5

·

verified ·

1 Parent(s): 7b6d2b8

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -479,9 +479,9 @@ evalplus.evaluate \
    </td>
    <td>84.70
    </td>
-   <td>
    </td>
-   <td>%
    </td>
   </tr>
   <tr>
@@ -489,9 +489,9 @@ evalplus.evaluate \
    </td>
    <td>79.50
    </td>
-   <td>
    </td>
-   <td>%
    </td>
   </tr>
   <tr>

    </td>
    <td>84.70
    </td>
+   <td>84.20
    </td>
+   <td>99.4%
    </td>
   </tr>
   <tr>
    </td>
    <td>79.50
    </td>
+   <td>81.00
    </td>
+   <td>101.9%
    </td>
   </tr>
   <tr>