RedHatAI
/

Qwen2.5-VL-3B-Instruct-quantized.w8a8

Image-Text-to-Text

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

shubhrapandit commited on 11 days ago

Commit

8c3aab4

·

verified ·

1 Parent(s): a0de4a5

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -285,9 +285,9 @@ lm_eval \
     <tr>
       <td rowspan="2"><b>Text</b></td>
       <td>MGSM (CoT)</td>
-      <td>52.49</td>
-      <td>50.42</td>
-      <td>96.05%</td>
     </tr>
     <tr>
       <td>MMLU (5-shot)</td>

     <tr>
       <td rowspan="2"><b>Text</b></td>
       <td>MGSM (CoT)</td>
+      <td>43.69</td>
+      <td>41.98</td>
+      <td>96.09%</td>
     </tr>
     <tr>
       <td>MMLU (5-shot)</td>