Update README.md

README.md

@@ -8,6 +8,16 @@ This model is a Mixture of Experts (MoE) merger of the following two models:
 - [rinna/youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction)
 - [rinna/youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat)
 
+## 🏆 Evaluation
+
+|                             Model                              |JCommonsenseQA|JNLI|MARC-ja|JSQuAD|4-AVERAGE|
+|                                                                |(3-shot)|(3-shot)|(0-shot)|(2-shot)|  |
+|                                                                |(acc.) |(balanced acc.)|(balanced acc.)|(F1)|  |
+|----------------------------------------------------------------|------:|------:|---------:|-------:|------:|
+|[**youri-2x7b_dev**](https://huggingface.co/mlabonne/phixtral-2x2_8)|   **91.15**|  **71.03**|     **?**|   **89.46**|  **?**|
+|[youri-7b-instruction](https://huggingface.co/rinna/youri-7b-instruction)|  88.83|  63.56|     93.78|    92.19|  84.59|
+|[youri-7b-chat](https://huggingface.co/rinna/youri-7b-chat)|  91.78|  70.35|     96.69|    79.62|  84.61|
+
 ## 🧩 Configuration
 
 The model has been made with a custom version of the [mergekit](https://github.com/cg123/mergekit) library (mixtral branch) and the following configuration: