RedHatAI
/

Meta-Llama-3.1-70B-Instruct-quantized.w8a8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

mgoin commited on Aug 15, 2024

Commit

e872e9d

·

verified ·

1 Parent(s): dff3199

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -146,7 +146,7 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
    </td>
    <td><strong>Meta-Llama-3.1-70B-Instruct </strong>
    </td>
-   <td><strong>Meta-Llama-3.1-70B-Instruct-quantized.w8a16 (this model)</strong>
    </td>
    <td><strong>Recovery</strong>
    </td>

    </td>
    <td><strong>Meta-Llama-3.1-70B-Instruct </strong>
    </td>
+   <td><strong>Meta-Llama-3.1-70B-Instruct-quantized.w8a8 (this model)</strong>
    </td>
    <td><strong>Recovery</strong>
    </td>