Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,14 +1,108 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
 - Fizzarolli/MN-12b-Sunrose
 - anthracite-org/magnum-v4-12b
 - mistralai/Mistral-Nemo-Instruct-2407
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: MN-12B-Inferor-v0.1
+  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: 63.47
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.1
+      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: 30.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.1
+      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: 11.78
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.1
+      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: 10.07
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.1
+      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: 15.05
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.1
+      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: 29.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.1
+      name: Open LLM Leaderboard
 ---
 # inferor 0.1
 
@@ -52,3 +146,17 @@ slices:
   - layer_range: [0, 40]
     model: mistralai/Mistral-Nemo-Instruct-2407
 ```
+
+# [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_Svak__MN-12B-Inferor-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.80|
+|IFEval (0-Shot)    |63.47|
+|BBH (3-Shot)       |30.85|
+|MATH Lvl 5 (4-Shot)|11.78|
+|GPQA (0-shot)      |10.07|
+|MuSR (0-shot)      |15.05|
+|MMLU-PRO (5-shot)  |29.58|
+