Adding Evaluation Results (#1)

- Adding Evaluation Results (42e9e9ff738f008320e0b81131bcc7e2295eb849)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,15 +1,109 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - lemon07r/Gemma-2-Ataraxy-9B
 - wzhouad/gemma-2-9b-it-WPO-HB
 - rtzr/ko-gemma-2-9b-it
 - ghost613/gemma9_on_korean_summary_events
 - rtzr/ko-gemma-2-9b-it
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Gemma-Ko-Merge
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 64.16
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Gunulhona/Gemma-Ko-Merge
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 38.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Gunulhona/Gemma-Ko-Merge
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.15
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Gunulhona/Gemma-Ko-Merge
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.41
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Gunulhona/Gemma-Ko-Merge
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Gunulhona/Gemma-Ko-Merge
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 31.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Gunulhona/Gemma-Ko-Merge
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -62,3 +156,17 @@ merge_method: breadcrumbs_ties
 base_model: lemon07r/Gemma-2-Ataraxy-9B
 dtype: bfloat16
 ```
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Gunulhona__Gemma-Ko-Merge)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.94|
+|IFEval (0-Shot)    |64.16|
+|BBH (3-Shot)       |38.79|
+|MATH Lvl 5 (4-Shot)| 0.15|
+|GPQA (0-shot)      |11.41|
+|MuSR (0-shot)      | 9.12|
+|MMLU-PRO (5-shot)  |31.99|
+