Hugging Face's logo

neuralmagic
/
Meta-Llama-3.1-8B-Instruct-quantized.w8a8

Text Generation
Transformers
Safetensors
llama
int8
vllm
conversational
text-generation-inference
Inference Endpoints
8-bit precision
compressed-tensors
Model card Files Community
2
alexmarques commited on
Commit
9495321
•
1 Parent(s): be1f41f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -206,9 +206,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
206
  </td>
207
  <td>78.06
208
  </td>
209
- <td>77.27
210
  </td>
211
- <td>99.0%
212
  </td>
213
  </tr>
214
  <tr>
@@ -216,9 +216,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
216
  </td>
217
  <td>54.48
218
  </td>
219
- <td>54.17
220
  </td>
221
- <td>99.4%
222
  </td>
223
  </tr>
224
  <tr>
@@ -226,9 +226,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
226
  </td>
227
  <td><strong>74.05</strong>
228
  </td>
229
- <td><strong>73.99</strong>
230
  </td>
231
- <td><strong>99.9%</strong>
232
  </td>
233
  </tr>
234
  </table>
 
206
  </td>
207
  <td>78.06
208
  </td>
209
+ <td>78.45
210
  </td>
211
+ <td>100.5%
212
  </td>
213
  </tr>
214
  <tr>
 
216
  </td>
217
  <td>54.48
218
  </td>
219
+ <td>54.65
220
  </td>
221
+ <td>100.3%
222
  </td>
223
  </tr>
224
  <tr>
 
226
  </td>
227
  <td><strong>74.05</strong>
228
  </td>
229
+ <td><strong>74.22</strong>
230
  </td>
231
+ <td><strong>100.2%</strong>
232
  </td>
233
  </tr>
234
  </table>