Adding Evaluation Results (#2)

- Adding Evaluation Results (338b65799bb0c4e739ef1ca338340b978bbf780a)

README.md

@@ -1,15 +1,109 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - RozGrov/NemoDori-v0.2.2-12B-MN-ties
 - spow12/ChatWaifu_v1.4
 - Nohobby/MN-12B-Siskin-v0.2
 - GalrionSoftworks/Canidori-12B-v1
 - ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: MN-Chinofun
+  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: 61.1
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun
+      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: 28.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun
+      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: 10.5
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun
+      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: 6.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun
+      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: 10.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun
+      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: 28.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/MN-Chinofun
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -42,3 +136,17 @@ merge_method: model_stock
 base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
 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)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.26|
+|IFEval (0-Shot)    |61.10|
+|BBH (3-Shot)       |28.48|
+|MATH Lvl 5 (4-Shot)|10.50|
+|GPQA (0-shot)      | 6.15|
+|MuSR (0-shot)      |10.38|
+|MMLU-PRO (5-shot)  |28.92|
+