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

@@ -1,17 +1,112 @@
 ---
+language:
+- en
+license: mit
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - gz987/qwen2.5-7b-cabs-v0.3
 - gz987/qwen2.5-7b-cabs-v0.4
 - gz987/qwen2.5-7b-cabs-v0.1
 - gz987/qwen2.5-7b-cabs-v0.2
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: mit
-language:
-- en
 pipeline_tag: text-generation
+model-index:
+- name: Clarus-7B-v0.2
+  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: 76.79
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
+      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: 36.02
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
+      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: 48.56
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
+      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: 6.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
+      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: 15.07
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
+      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: 37.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
+      name: Open LLM Leaderboard
 ---
 # Merged Model
 
@@ -48,4 +143,17 @@ models:
   - model:           gz987/qwen2.5-7b-cabs-v0.4
   - model:           gz987/qwen2.5-7b-cabs-v0.2
   - model:           gz987/qwen2.5-7b-cabs-v0.1
-```
+```
+# [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/suayptalha__Clarus-7B-v0.2-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.86|
+|IFEval (0-Shot)    |76.79|
+|BBH (3-Shot)       |36.02|
+|MATH Lvl 5 (4-Shot)|48.56|
+|GPQA (0-shot)      | 6.94|
+|MuSR (0-shot)      |15.07|
+|MMLU-PRO (5-shot)  |37.78|
+