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

@@ -1,4 +1,8 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - grimjim/magnum-consolidatum-v1-12b
 - spow12/ChatWaifu_v1.4
@@ -6,11 +10,101 @@ base_model:
 - Nohobby/MN-12B-Siskin-v0.2
 - ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
 - RozGrov/NemoDori-v0.2.2-12B-MN-ties
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: MN-Chinofun-12B-2
+  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: 61.71
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun-12B-2
+      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: 29.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun-12B-2
+      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: 11.18
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun-12B-2
+      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: 7.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun-12B-2
+      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: 13.35
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun-12B-2
+      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: 29.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun-12B-2
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -45,3 +139,17 @@ merge_method: model_stock
 base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
 dtype: bfloat16
 ```
+
+# [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_djuna__MN-Chinofun-12B-2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.37|
+|IFEval (0-Shot)    |61.71|
+|BBH (3-Shot)       |29.53|
+|MATH Lvl 5 (4-Shot)|11.18|
+|GPQA (0-shot)      | 7.38|
+|MuSR (0-shot)      |13.35|
+|MMLU-PRO (5-shot)  |29.06|
+