Adding Evaluation Results (#1)

- Adding Evaluation Results (581a874450828d29e8a6eb6ab4da0e21ad87facd)

README.md

@@ -1,16 +1,111 @@
 ---
-base_model:
-- bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
-- bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+language:
+- en
+license: mit
 library_name: transformers
 tags:
 - mergekit
 - merge
 - not-for-all-audiences
-license: mit
-language:
-- en
+base_model:
+- bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V
+- bamec66557/MISCHIEVOUS-12B-Mix_0.4v
 pipeline_tag: text-generation
+model-index:
+- name: MISCHIEVOUS-12B-Mix_III_IV_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: 40.31
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_IV_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: 34.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_IV_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: 12.84
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_IV_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_IV_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: 12.34
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_IV_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: 29.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_III_IV_V
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -69,4 +164,17 @@ postprocessing:
   - operation: gaussian_smoothing
     sigma: 1.2
   - operation: normalize
-```
+```
+# [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_IV_V-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.22|
+|IFEval (0-Shot)    |40.31|
+|BBH (3-Shot)       |34.85|
+|MATH Lvl 5 (4-Shot)|12.84|
+|GPQA (0-shot)      | 9.40|
+|MuSR (0-shot)      |12.34|
+|MMLU-PRO (5-shot)  |29.60|
+