Adding Evaluation Results (#1)

- Adding Evaluation Results (e8f856392e4ff2be4c5b6cedab3d4aa5c1d5764f)

README.md

@@ -1,15 +1,110 @@
 ---
-base_model:
-- bamec66557/mergekit-slerp-uhnpbqg
-- bamec66557/mergekit-slerp-tsgkafq
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
 - not-for-all-audiences
-license: apache-2.0
-language:
-- en
+base_model:
+- bamec66557/mergekit-slerp-uhnpbqg
+- bamec66557/mergekit-slerp-tsgkafq
+model-index:
+- name: MISCHIEVOUS-12B-Mix_III_ex_V
+  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: 43.16
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
+      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: 34.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
+      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: 13.14
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
+      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: 9.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
+      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: 12.77
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
+      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: 29.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -144,4 +239,17 @@ ties:
   method: greedy  # Options: greedy, optimal, random
   layers: [0, 10, 20, 30]  # Example layers for ties merging
 
-```
+```
+# [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/bamec66557__MISCHIEVOUS-12B-Mix_III_ex_V-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.80|
+|IFEval (0-Shot)    |43.16|
+|BBH (3-Shot)       |34.87|
+|MATH Lvl 5 (4-Shot)|13.14|
+|GPQA (0-shot)      | 9.40|
+|MuSR (0-shot)      |12.77|
+|MMLU-PRO (5-shot)  |29.43|
+