Update README.md

README.md

@@ -16,28 +16,104 @@ model-index:
   results:
   - task:
       type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
     metrics:
-    - name: ARC (25-Shot)
-      type: arc_challenge (25-Shot)
+    - type: acc_norm
       value: 60.07
-    - name: Hellaswag (10-Shot)
-      type: Hellaswag (10-Shot)
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
       value: 83.43
-    - name: TruthfulQA
-      type: TruthfulQA
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
       value: 52.06
-    - name: GSM8K (5-Shot)
-      type: GSM8K (5-Shot)
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
       value: 38.97
-    - name: Winogrande (5-Shot)
-      type: Winogrande (5-Shot)
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
       value: 78.61
-    - name: MMLU (5-Shot)
-      type: MMLU (5-Shot)
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
       value: 60.07
+      name: accuracy
     source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
 ---
 # Model Card for Cymist2-v0.2-SFT
 ### Model Description