Safetensors
llama
falcon3
4-bit precision
gptq

Update README.md

#1
by karnakar - opened
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -113,24 +113,24 @@ We report in the following table our internal pipeline benchmarks:
113
  <tbody>
114
  <tr>
115
  <td>MMLU</td>
116
- <td>55.70</td>
117
- <td>55.79</td>
118
- <td>53.30</td>
119
- <td>53.25</td>
120
  </tr>
121
  <tr>
122
  <td>MMLU-PRO</td>
123
- <td>30.00</td>
124
- <td>30.27</td>
125
- <td>28.37</td>
126
- <td>25.88</td>
127
  </tr>
128
  <tr>
129
  <td>IFEval</td>
130
- <td>69.07</td>
131
- <td>68.34</td>
132
- <td>67.85</td>
133
- <td>62.83</td>
134
  </tr>
135
  </tbody>
136
  </table>
 
113
  <tbody>
114
  <tr>
115
  <td>MMLU</td>
116
+ <td>55.7</td>
117
+ <td>55.8</td>
118
+ <td>53.3</td>
119
+ <td>53.3</td>
120
  </tr>
121
  <tr>
122
  <td>MMLU-PRO</td>
123
+ <td>30.0</td>
124
+ <td>30.3</td>
125
+ <td>28.4</td>
126
+ <td>25.9</td>
127
  </tr>
128
  <tr>
129
  <td>IFEval</td>
130
+ <td>69.1</td>
131
+ <td>68.4</td>
132
+ <td>67.9</td>
133
+ <td>62.9</td>
134
  </tr>
135
  </tbody>
136
  </table>