Hugging Face's logo

nvidia
/
Llama-3.1-8B-Instruct-FP8

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
Community
1
omrialmog commited on
Commit
eb9e064
·
verified ·
1 Parent(s): e25ad2e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -4
README.md CHANGED
@@ -96,17 +96,19 @@ Please refer to the [TensorRT-LLM benchmarking documentation](https://github.com
96
  </td>
97
  <td><strong>IFEVAL</strong>
98
  </td>
 
 
99
  </tr>
100
  <tr>
101
  <td>BF16
102
  </td>
103
- <td>69.5
104
  </td>
105
- <td>83.5
106
  </td>
107
- <td>84.0
108
  </td>
109
- <td>81.2
110
  </td>
111
  <td>8,579.93
112
  </td>
 
96
  </td>
97
  <td><strong>IFEVAL</strong>
98
  </td>
99
+ <td><strong>TPS</strong>
100
+ </td>
101
  </tr>
102
  <tr>
103
  <td>BF16
104
  </td>
105
+ <td>69.4
106
  </td>
107
+ <td>84.5
108
  </td>
109
+ <td>83.4
110
  </td>
111
+ <td>80.4
112
  </td>
113
  <td>8,579.93
114
  </td>