Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,15 +1,110 @@
 ---
-base_model:
-- lemon07r/Gemma-2-Ataraxy-9B
-- TheDrummer/Gemmasutra-9B-v1
+license: apache-2.0
+library_name: transformers
 tags:
 - merge
 - mergekit
 - lazymergekit
 - lemon07r/Gemma-2-Ataraxy-9B
 - TheDrummer/Gemmasutra-9B-v1
-license: apache-2.0
-library_name: transformers
+base_model:
+- lemon07r/Gemma-2-Ataraxy-9B
+- TheDrummer/Gemmasutra-9B-v1
+model-index:
+- name: Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+  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: 76.49
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      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: 42.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      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: 1.74
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      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: 10.74
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      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: 12.39
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      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: 35.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open LLM Leaderboard
 ---
 
 # Gemma-2-Ataraxy-Gemmasutra-9B-slerp
@@ -62,4 +157,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_recoilme__Gemma-2-Ataraxy-Gemmasutra-9B-slerp)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |29.87|
+|IFEval (0-Shot)    |76.49|
+|BBH (3-Shot)       |42.25|
+|MATH Lvl 5 (4-Shot)| 1.74|
+|GPQA (0-shot)      |10.74|
+|MuSR (0-shot)      |12.39|
+|MMLU-PRO (5-shot)  |35.63|
+