Adding Evaluation Results (#6)

- Adding Evaluation Results (f24f9a8d61a731c75f490aa04e2f063b63cc92b3)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,13 +1,107 @@
-
 ---
-base_model:
-- princeton-nlp/gemma-2-9b-it-SimPO
-- nbeerbower/gemma2-gutenberg-9B
+license: gemma
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: gemma
+base_model:
+- princeton-nlp/gemma-2-9b-it-SimPO
+- nbeerbower/gemma2-gutenberg-9B
+model-index:
+- name: Gemma-2-Ataraxy-9B
+  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: 30.09
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-9B
+      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: 42.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-9B
+      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: 0.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-9B
+      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: 11.3
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-9B
+      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: 14.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-9B
+      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: 35.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-9B
+      name: Open LLM Leaderboard
 ---
 # Gemma-2-Ataraxy-9B
 
@@ -97,3 +191,17 @@ slices:
   - layer_range: [0, 42]
     model: nbeerbower/gemma2-gutenberg-9B
 ```
+
+# [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_lemon07r__Gemma-2-Ataraxy-9B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.43|
+|IFEval (0-Shot)    |30.09|
+|BBH (3-Shot)       |42.03|
+|MATH Lvl 5 (4-Shot)| 0.83|
+|GPQA (0-shot)      |11.30|
+|MuSR (0-shot)      |14.47|
+|MMLU-PRO (5-shot)  |35.85|
+