Adding Evaluation Results (#1)

- Adding Evaluation Results (06477b02946050e59f67ea8f9fff140cdae84df7)

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+library_name: transformers
 tags:
 - merge
 - mergekit
@@ -9,7 +10,101 @@ tags:
 base_model:
 - bunnycore/QandoraExp-7B
 - trollek/Qwen2.5-7B-CySecButler-v0.1
-library_name: transformers
+model-index:
+- name: Qwen2.5-7B-Qandora-CySec
+  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: 67.73
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-Qandora-CySec
+      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: 36.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-Qandora-CySec
+      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: 22.89
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-Qandora-CySec
+      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: 6.71
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-Qandora-CySec
+      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: 13.41
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-Qandora-CySec
+      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: 38.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-Qandora-CySec
+      name: Open LLM Leaderboard
 ---
 # Qwen2.5-7B-Qandora-CySec
 
@@ -164,4 +259,17 @@ If you use this model, please cite this repository and the original base models.
 
 ## 💡 Tags
 
-merge, mergekit, lazymergekit, bunnycore/QandoraExp-7B, trollek/Qwen2.5-7B-CySecButler-v0.1, cybersecurity, Q&A
+merge, mergekit, lazymergekit, bunnycore/QandoraExp-7B, trollek/Qwen2.5-7B-CySecButler-v0.1, cybersecurity, Q&A
+# [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_ZeroXClem__Qwen2.5-7B-Qandora-CySec)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |30.95|
+|IFEval (0-Shot)    |67.73|
+|BBH (3-Shot)       |36.26|
+|MATH Lvl 5 (4-Shot)|22.89|
+|GPQA (0-shot)      | 6.71|
+|MuSR (0-shot)      |13.41|
+|MMLU-PRO (5-shot)  |38.72|
+