Hugging Face's logo

neuralmagic
/
Meta-Llama-3.1-70B-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
3
alexmarques commited on
Commit
215dd48
·
verified ·
1 Parent(s): 6bf2cfa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -197,9 +197,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
197
  </td>
198
  <td>86.66
199
  </td>
200
- <td>86.19
201
  </td>
202
- <td>99.5%
203
  </td>
204
  </tr>
205
  <tr>
@@ -207,9 +207,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
207
  </td>
208
  <td>85.32
209
  </td>
210
- <td>85.00
211
  </td>
212
- <td>99.6%
213
  </td>
214
  </tr>
215
  <tr>
@@ -217,9 +217,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
217
  </td>
218
  <td>60.65
219
  </td>
220
- <td>60.69
221
  </td>
222
- <td>100.1%
223
  </td>
224
  </tr>
225
  <tr>
@@ -227,9 +227,9 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
227
  </td>
228
  <td><strong>84.50</strong>
229
  </td>
230
- <td><strong>84.10</strong>
231
  </td>
232
- <td><strong>99.6%</strong>
233
  </td>
234
  </tr>
235
  </table>
 
197
  </td>
198
  <td>86.66
199
  </td>
200
+ <td>86.65
201
  </td>
202
+ <td>100.0%
203
  </td>
204
  </tr>
205
  <tr>
 
207
  </td>
208
  <td>85.32
209
  </td>
210
+ <td>85.10
211
  </td>
212
+ <td>100.1%
213
  </td>
214
  </tr>
215
  <tr>
 
217
  </td>
218
  <td>60.65
219
  </td>
220
+ <td>61.43
221
  </td>
222
+ <td>101.3%
223
  </td>
224
  </tr>
225
  <tr>
 
227
  </td>
228
  <td><strong>84.50</strong>
229
  </td>
230
+ <td><strong>84.33</strong>
231
  </td>
232
+ <td><strong>99.9%</strong>
233
  </td>
234
  </tr>
235
  </table>