Adding Evaluation Results (#1)

- Adding Evaluation Results (6b8043413547bf69d45be3b0cd916d99e210d904)

README.md

@@ -1,5 +1,8 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 tags:
 - merge
 - mergekit
@@ -15,9 +18,101 @@ base_model:
 - allknowingroger/HomerSlerp1-7B
 - bunnycore/Qwen2.5-7B-Instruct-Fusion
 - bunnycore/Qandora-2.5-7B-Creative
-language:
-- en
-library_name: transformers
+model-index:
+- name: Qwen2.5-7B-HomerCreative-Mix
+  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: 78.35
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
+      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: 36.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
+      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: 32.33
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
+      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: 6.6
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
+      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: 13.77
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
+      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: 38.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
+      name: Open LLM Leaderboard
 ---
 
 # ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
@@ -179,4 +274,17 @@ This model is open-sourced under the **Apache-2.0 License**.
 - `allknowingroger/HomerSlerp1-7B`
 - `newsbang/Homer-v0.5-Qwen2.5-7B`
 
----
+---
+# [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-HomerCreative-Mix)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |34.35|
+|IFEval (0-Shot)    |78.35|
+|BBH (3-Shot)       |36.77|
+|MATH Lvl 5 (4-Shot)|32.33|
+|GPQA (0-shot)      | 6.60|
+|MuSR (0-shot)      |13.77|
+|MMLU-PRO (5-shot)  |38.30|
+