Adding Evaluation Results

README.md

@@ -4,6 +4,101 @@ language:
 license: llama3.1
 tags:
 - moe
+model-index:
+- name: L3.1-ClaudeMaid-4x8B
+  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: 66.96
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xxx777xxxASD/L3.1-ClaudeMaid-4x8B
+      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: 29.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xxx777xxxASD/L3.1-ClaudeMaid-4x8B
+      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: 12.84
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xxx777xxxASD/L3.1-ClaudeMaid-4x8B
+      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: 5.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xxx777xxxASD/L3.1-ClaudeMaid-4x8B
+      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: 13.75
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xxx777xxxASD/L3.1-ClaudeMaid-4x8B
+      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: 28.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=xxx777xxxASD/L3.1-ClaudeMaid-4x8B
+      name: Open LLM Leaderboard
 ---
 
 <style>
@@ -72,4 +167,17 @@ Try [this koboldcpp version](https://github.com/Nexesenex/kobold.cpp/releases/ta
 - [aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored](https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored)
 
 
-## Prompt format: Llama 3
+## Prompt format: Llama 3
+# [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_xxx777xxxASD__L3.1-ClaudeMaid-4x8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.19|
+|IFEval (0-Shot)    |66.96|
+|BBH (3-Shot)       |29.44|
+|MATH Lvl 5 (4-Shot)|12.84|
+|GPQA (0-shot)      | 5.48|
+|MuSR (0-shot)      |13.75|
+|MMLU-PRO (5-shot)  |28.67|
+