Hugging Face's logo

amd
/
Llama-3.2-90B-Vision-Instruct-FP8-KV

Safetensors
mllama
fp8
Model card Files Community
10
haoyang-amd commited on
Commit
7b30605
·
verified ·
1 Parent(s): 112d1a3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -57,7 +57,7 @@ The quantization evaluation results are conducted in pseudo-quantization mode, w
57
  </td>
58
  <td>3.7805
59
  </td>
60
- <td>3.8570
61
  </td>
62
  </tr>
63
 
 
57
  </td>
58
  <td>3.7805
59
  </td>
60
+ <td>3.8547
61
  </td>
62
  </tr>
63