Adding Evaluation Results

README.md

@@ -8,15 +8,115 @@ model-index:
 - name: NinjaDolphin-7B
   results:
   - task:
-      type: text-generation             # Required. Example: automatic-speech-recognition
+      type: text-generation
     dataset:
-      type: openai_humaneval         # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
-      name: HumanEval         # Required. A pretty name for the dataset. Example: Common Voice (French)
+      name: HumanEval
+      type: openai_humaneval
     metrics:
-      - type: pass@1         # Required. Example: wer. Use metric id from https://hf.co/metrics
-        value: 52.4390243902439       # Required. Example: 20.90
-        name: pass@1         # Optional. Example: Test WER
-        verified: false
+    - type: pass@1
+      value: 52.4390243902439
+      name: pass@1
+      verified: false
+  - 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: 65.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/NinjaDolphin-7B
+      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: 85.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/NinjaDolphin-7B
+      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: 64.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/NinjaDolphin-7B
+      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: 54.94
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/NinjaDolphin-7B
+      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: 80.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/NinjaDolphin-7B
+      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: 67.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/NinjaDolphin-7B
+      name: Open LLM Leaderboard
 ---
 
 # NinjaDolphin-7B
@@ -93,3 +193,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |Winogrande (5-shot)              |80.27|
 |GSM8k (5-shot)                   |67.85|
 
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_FelixChao__NinjaDolphin-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.74|
+|AI2 Reasoning Challenge (25-Shot)|65.61|
+|HellaSwag (10-Shot)              |85.35|
+|MMLU (5-Shot)                    |64.43|
+|TruthfulQA (0-shot)              |54.94|
+|Winogrande (5-shot)              |80.27|
+|GSM8k (5-shot)                   |67.85|
+