neuralmagic
/

Meta-Llama-3.1-405B-Instruct-quantized.w8a8

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions Community

alexmarques commited on Sep 30, 2024

Commit

490a062

·

verified ·

1 Parent(s): 533cdce

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -170,9 +170,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
    </td>
    <td>87.38
    </td>
-   <td>86.76
    </td>
-   <td>99.3%
    </td>
   </tr>
   <tr>
@@ -230,7 +230,7 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
    </td>
    <td><strong>86.75</strong>
    </td>
-   <td><strong>86.11</strong>
    </td>
    <td><strong>99.3%</strong>
    </td>

    </td>
    <td>87.38
    </td>
+   <td>87.05
    </td>
+   <td>99.6%
    </td>
   </tr>
   <tr>
    </td>
    <td><strong>86.75</strong>
    </td>
+   <td><strong>86.15</strong>
    </td>
    <td><strong>99.3%</strong>
    </td>