added evaluation results

README.md

@@ -7,7 +7,49 @@ tags:
 - generated_from_trainer
 model-index:
 - name: SmolLM-135M-instruct-de-merged
-  results: []
+  results:
+      - task:
+          type: text-generation
+        dataset:
+          name: openai/MMMLU
+          type: mmlu
+        metrics:
+          - name: MMMLU(DE_DE) (0-Shot)
+            type: MMMLU(DE_DE) (0-Shot)
+            value: 25.57
+            verified: false
+      - task:
+          type: text-generation
+        dataset:
+          name: alexandrainst/m_arc
+          type: arc
+        metrics:
+          - name: ARC Challenge (DE) (0-Shot)
+            type: ARC Challenge (DE) (0-Shot)
+            value: 24.29
+            verified: false
+      - task:
+          type: text-generation
+        dataset:
+          name: deutsche-telekom/Ger-RAG-eval
+          type: Ger-RAG-eval
+        metrics:
+          - name: Ger-RAG-eval Choose Context By Question
+            type: Ger-RAG-eval Task 1
+            value: 25.2
+            verified: false
+          - name: Ger-RAG-eval Choose Question By Context
+            type: Ger-RAG-eval Task 2
+            value: 27.1
+            verified: false
+          - name: Ger-RAG-eval Context Question Match
+            type: Ger-RAG-eval Task 3
+            value: 50.9
+            verified: false
+          - name: Ger-RAG-eval Question Answer Match
+            type: Ger-RAG-eval Task 4
+            value: 50.0
+            verified: false
 language:
 - de
 pipeline_tag: text-generation