Update README.md

README.md

@@ -56,42 +56,75 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 I encourage you to provide feedback on the model's performance. If you'd like to create your own quantizations, feel free to do so and let me know how it works for you!
 
 model-index:
-  - name: P0x0/Astra-v1-12B
-    results:
-      - task:
-          type: text-generation
-        dataset:
-          type: benchmark
-          name: AI2 Reasoning Challenge (25-Shot)
-        metrics:
-          - name: Average
-            type: Average
-            value: 19.46
-            verified: false
-          - name: IFEval
-            type: IFEval
-            value: 28.06
-            verified: false
-          - name: BBH
-            type: BBH
-            value: 31.81
-            verified: false
-          - name: MATH Lvl 5
-            type: MATH Lvl 5
-            value: 9.67
-            verified: false
-          - name: GPQA
-            type: GPQA
-            value: 8.5
-            verified: false
-          - name: MUSR
-            type: MUSR
-            value: 11.38
-            verified: false
-          - name: MMLU-PRO
-            type: MMLU-PRO
-            value: 27.34
-            verified: false
-        source:
-          name: Open LLM Leaderboard
-          url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
+- name: P0x0/Astra-v1-12B
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: Aggregate
+      name: Average
+    metrics:
+    - name: Average
+      type: Average
+      value: 19.46
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: IFEval
+      name: IFEval
+    metrics:
+    - name: Score
+      type: IFEval
+      value: 28.06
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: BBH
+      name: BBH
+    metrics:
+    - name: Score
+      type: BBH
+      value: 31.81
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: MATH Lvl 5
+      name: MATH Lvl 5
+    metrics:
+    - name: Score
+      type: MATH Lvl 5
+      value: 9.67
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: GPQA
+      name: GPQA
+    metrics:
+    - name: Score
+      type: GPQA
+      value: 8.5
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: MUSR
+      name: MUSR
+    metrics:
+    - name: Score
+      type: MUSR
+      value: 11.38
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: MMLU-PRO
+      name: MMLU-PRO
+    metrics:
+    - name: Score
+      type: MMLU-PRO
+      value: 27.34
+      verified: false