eval

README.md

@@ -35,6 +35,18 @@ model_type: llama
 model-index:
 - name: Llama3.2-3B-ShiningValiant2
   results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 69.85
+      name: strict accuracy
   - task:
       type: text-generation
       name: Text Generation