Adding Evaluation Results (#1)

- Adding Evaluation Results (c491f799c755efb3ebea420935a37b6931ba043e)


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

README.md

@@ -1,14 +1,108 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - nbeerbower/Gemma2-Gutenberg-Doppel-9B
 - ifable/gemma-2-Ifable-9B
 - unsloth/gemma-2-9b-it
 - wzhouad/gemma-2-9b-it-WPO-HB
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Gemma-2-Ataraxy-v3i-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: 42.03
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-v3i-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: 38.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-v3i-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: 0.15
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-v3i-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: 10.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-v3i-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: 1.76
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-v3i-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: 35.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Gemma-2-Ataraxy-v3i-9B
+      name: Open LLM Leaderboard
 ---
 # Gemma-2-Ataraxy-v3i-9B
 
@@ -65,3 +159,17 @@ slices:
       density: 0.25
       weight: 0.4
 ```
+
+# [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-v3i-9B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.29|
+|IFEval (0-Shot)    |42.03|
+|BBH (3-Shot)       |38.24|
+|MATH Lvl 5 (4-Shot)| 0.15|
+|GPQA (0-shot)      |10.40|
+|MuSR (0-shot)      | 1.76|
+|MMLU-PRO (5-shot)  |35.18|
+