Update README.md

README.md

@@ -2,6 +2,8 @@
 model-index:
 - name: Dolphin2.1-OpenOrca-7B
   results:
+
+
   # AI2 Reasoning Challenge (25-Shot)
   - task: 
       type: text-generation
@@ -21,6 +23,7 @@ model-index:
       name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B
       
+
   # HellaSwag (10-shot)
   - task: 
       type: text-generation
@@ -39,77 +42,81 @@ model-index:
       name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B
 
-  # TruthfulQA (0-shot)
+
+  # MMLU (5-Shot)
   - task: 
       type: text-generation
       name: Text Generation
     dataset:
-      name: TruthfulQA (0-shot)
-      type: truthful_qa
-      config: multiple_choice
-      split: validation
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
       args:
-        num_few_shot: 0
+        num_few_shot: 5
     metrics:
-       - type: mc2
-         value: 53.84
+       - type: acc
+         name: accuracy
+         value: 62.66
     source:
       name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B
 
-  # GSM8k (5-shot)
+
+  # TruthfulQA (0-shot)
   - task: 
       type: text-generation
       name: Text Generation
     dataset:
-      name: GSM8k (5-shot)
-      type: gsm8k
-      config: main
-      split: test
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
       args:
-        num_few_shot: 5
+        num_few_shot: 0
     metrics:
-       - type: acc
-         name: accuracy
-         value: 19.94
+       - type: mc2
+         value: 53.84
     source:
       name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B
 
-  # MMLU (5-Shot)
+
+  # Winogrande (5-shot)
   - task: 
       type: text-generation
       name: Text Generation
     dataset:
-      name: MMLU (5-Shot)
-      type: cais/mmlu
-      config: all
-      split: test
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
       args:
         num_few_shot: 5
     metrics:
        - type: acc
          name: accuracy
-         value: 62.66
+         value: 78.22
     source:
       name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B
 
-  # Winogrande (5-shot)
+
+  # GSM8k (5-shot)
   - task: 
       type: text-generation
       name: Text Generation
     dataset:
-      name: Winogrande (5-shot)
-      type: winogrande
-      config: winogrande_xl
-      split: validation
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
       args:
         num_few_shot: 5
     metrics:
        - type: acc
          name: accuracy
-         value: 78.22
+         value: 19.94
     source:
       name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B