Adding Evaluation Results (#2)

- Adding Evaluation Results (d0ec188ac23ced2af424f5be07e050769fe630e1)

README.md

@@ -1,16 +1,111 @@
 ---
+license: mit
+library_name: transformers
+tags:
+- mergekit
+- merge
+- phi4
 base_model:
 - unsloth/phi-4
 - bunnycore/Phi-4-Avg
 - prithivMLmods/Phi-4-Empathetic
 - prithivMLmods/Phi-4-Math-IO
 - prithivMLmods/Phi-4-QwQ
-library_name: transformers
-tags:
-- mergekit
-- merge
-- phi4
-license: mit
+model-index:
+- name: Phi-4-Model-Stock
+  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: 68.79
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
+      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: 55.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
+      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: 38.6
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
+      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: 13.98
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
+      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: 15.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
+      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: 48.54
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -46,4 +141,17 @@ parameters:
 dtype: bfloat16
 tokenizer_source: unsloth/phi-4
 
-```
+```
+# [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/bunnycore__Phi-4-Model-Stock-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |40.06|
+|IFEval (0-Shot)    |68.79|
+|BBH (3-Shot)       |55.32|
+|MATH Lvl 5 (4-Shot)|38.60|
+|GPQA (0-shot)      |13.98|
+|MuSR (0-shot)      |15.12|
+|MMLU-PRO (5-shot)  |48.54|
+