Update README.md

README.md

@@ -12,31 +12,107 @@ language:
 pipeline_tag: text2text-generation
 base_model: mistralai/Mistral-7B-v0.3
 
+
 model-index:
-  - name: cymist-2-v03-SFT
-    results:
-      - task:
-          type: text-generation
-        metrics:
-          - name: ARC (25-Shot)
-            type:  arc_challenge (25-Shot)
-            value: 59.12
-          - name: Hellaswag (10-Shot)
-            type:  Hellaswag (10-Shot)
-            value: 82.56
-          - name: TruthfulQA
-            type:  TruthfulQA
-            value: 52.12
-          - name: GSM8K (5-Shot)
-            type: GSM8K (5-Shot)
-            value: 36.61
-          - name: Winogrande (5-Shot)
-            type: Winogrande (5-Shot)
-            value: 77.43
-          - name: MMLU (5-Shot)
-            type: MMLU (5-Shot)
-            value: 62.65
-            
+- name: cymist-2-v03-SFT
+  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:
+    - type: acc_norm
+      value: 59.12
+      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: 82.56
+      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: 52.12
+    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: 36.61
+      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: 77.43
+      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: 62.65
+      name: accuracy
             
 ---
 # Model Card for Cymist2-v0.3-SFT