Adding Evaluation Results

README.md

@@ -2,9 +2,125 @@
 license: apache-2.0
 datasets:
 - argilla/distilabel-intel-orca-dpo-pairs
+model-index:
+- name: WestLakeX-7B-EvoMerge-Variant2
+  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: 72.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WestLakeX-7B-EvoMerge-Variant2
+      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: 88.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WestLakeX-7B-EvoMerge-Variant2
+      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: 64.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WestLakeX-7B-EvoMerge-Variant2
+      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: 70.35
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WestLakeX-7B-EvoMerge-Variant2
+      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: 85.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WestLakeX-7B-EvoMerge-Variant2
+      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: 68.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WestLakeX-7B-EvoMerge-Variant2
+      name: Open LLM Leaderboard
 ---
 # WestLakeX-7B-EvoMerge
 This is the result of a small-scale [EvoMerge](https://github.com/BarryFutureman/EvoMerge).
 
 Zoom in to view the family tree:
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6599dc66eabe0f3e98de7cf6/970gRDjFSkI9_nvApvGlg.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6599dc66eabe0f3e98de7cf6/970gRDjFSkI9_nvApvGlg.png)
+# [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_BarryFutureman__WestLakeX-7B-EvoMerge-Variant2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.04|
+|AI2 Reasoning Challenge (25-Shot)|72.53|
+|HellaSwag (10-Shot)              |88.52|
+|MMLU (5-Shot)                    |64.77|
+|TruthfulQA (0-shot)              |70.35|
+|Winogrande (5-shot)              |85.79|
+|GSM8k (5-shot)                   |68.31|
+