Update README.md

README.md

@@ -25,7 +25,7 @@ language:
 - **Model Developers:** Neural Magic
 
 Quantized version of [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
-It achieves an average score of 68.77 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 69.33.
+It achieves an average score of 72.46 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 73.11.
 
 ### Model Optimizations
 
@@ -130,6 +130,7 @@ oneshot(
 ## Evaluation
 
 The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) leaderboard tasks (version 1) with the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command:
+A modified version of ARC-C was used for evaluations, in line with Llama 3.1's prompting.
 ```
 lm_eval \
   --model vllm \
@@ -163,13 +164,13 @@ lm_eval \
    </td>
   </tr>
   <tr>
-   <td>ARC Challenge (25-shot)
+   <td>ARC Challenge (0-shot)
    </td>
-   <td>60.41
+   <td>83.11
    </td>
-   <td>60.24
+   <td>82.34
    </td>
-   <td>99.72%
+   <td>99.07%
    </td>
   </tr>
   <tr>
@@ -215,11 +216,11 @@ lm_eval \
   <tr>
    <td><strong>Average</strong>
    </td>
-   <td><strong>69.33</strong>
+   <td><strong>73.11</strong>
    </td>
-   <td><strong>68.77</strong>
+   <td><strong>72.46</strong>
    </td>
-   <td><strong>99.20%</strong>
+   <td><strong>99.10%</strong>
    </td>
   </tr>
 </table>