Adding Evaluation Results

README.md

@@ -1,17 +1,112 @@
 ---
-license: apache-2.0
-license_link: https://huggingface.co/huihui-ai/QwQ-32B-Coder-Fusion-9010/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
-base_model: 
- - huihui-ai/QwQ-32B-Preview-abliterated
- - huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
+license: apache-2.0
+library_name: transformers
 tags:
 - chat
 - abliterated
 - uncensored
-library_name: transformers
+base_model:
+- huihui-ai/QwQ-32B-Preview-abliterated
+- huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
+license_link: https://huggingface.co/huihui-ai/QwQ-32B-Coder-Fusion-9010/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: QwQ-32B-Coder-Fusion-9010
+  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: 57.78
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
+      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: 53.02
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
+      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: 40.26
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
+      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: 14.88
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
+      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: 19.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
+      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: 51.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
+      name: Open LLM Leaderboard
 ---
 
 # huihui-ai/QwQ-32B-Coder-Fusion-9010
@@ -43,3 +138,17 @@ ollama run huihui_ai/qwq-fusion
 ```
 
 Other proportions can be obtained by visiting [huihui_ai/qwq-fusion](https://ollama.com/huihui_ai/qwq-fusion/tags).
+
+# [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_huihui-ai__QwQ-32B-Coder-Fusion-9010)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |39.43|
+|IFEval (0-Shot)    |57.78|
+|BBH (3-Shot)       |53.02|
+|MATH Lvl 5 (4-Shot)|40.26|
+|GPQA (0-shot)      |14.88|
+|MuSR (0-shot)      |19.52|
+|MMLU-PRO (5-shot)  |51.11|
+