Adding Evaluation Results

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- ycros/BagelMIsteryTour-v2-8x7B
-- smelborp/MixtralOrochi8x7B
-- cognitivecomputations/dolphin-2.7-mixtral-8x7b
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- ycros/BagelMIsteryTour-v2-8x7B
+- smelborp/MixtralOrochi8x7B
+- cognitivecomputations/dolphin-2.7-mixtral-8x7b
+model-index:
+- name: maid-yuzu-v7
+  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: 64.62
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rhplus0831/maid-yuzu-v7
+      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: 26.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rhplus0831/maid-yuzu-v7
+      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: 8.91
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rhplus0831/maid-yuzu-v7
+      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: 7.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rhplus0831/maid-yuzu-v7
+      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: 9.77
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rhplus0831/maid-yuzu-v7
+      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: 28.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rhplus0831/maid-yuzu-v7
+      name: Open LLM Leaderboard
 ---
 # maid-yuzu-v7
 
@@ -52,3 +146,17 @@ slices:
       model:
         path: ycros/BagelMIsteryTour-v2-8x7B
 ```
+
+# [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_rhplus0831__maid-yuzu-v7)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.38|
+|IFEval (0-Shot)    |64.62|
+|BBH (3-Shot)       |26.82|
+|MATH Lvl 5 (4-Shot)| 8.91|
+|GPQA (0-shot)      | 7.94|
+|MuSR (0-shot)      | 9.77|
+|MMLU-PRO (5-shot)  |28.22|
+