Update README.md

README.md

@@ -22,6 +22,28 @@ Wiederchat-7b is a merge of the following models using [LazyMergekit](https://co
 * [mayflowergmbh/Wiedervereinigung-7b-dpo-laser](https://huggingface.co/mayflowergmbh/Wiedervereinigung-7b-dpo-laser)
 * [cognitivecomputations/openchat-3.5-0106-laser](https://huggingface.co/cognitivecomputations/openchat-3.5-0106-laser)
 
+# Benchmark mt-bench-de
+Even before dpo-alignment this model performs quite good: 
+```json
+{
+    "first_turn": 7.46875,
+    "second_turn": 6.7875,
+    "categories": {
+        "writing": 8.55,
+        "roleplay": 8,
+        "reasoning": 5.3,
+        "math": 4.35,
+        "coding": 4.6,
+        "extraction": 8.4,
+        "stem": 8.575,
+        "humanities": 9.25
+    },
+    "average": 7.128125
+}
+
+```
+
+
 ## 🧩 Configuration
 
 ```yaml