Adding Evaluation Results (#1)

- Adding Evaluation Results (f5e3c2c42a2d8cf59a51ec0b4be1270c83047b0b)

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- prithivMLmods/Phi-4-o1
-- bunnycore/Phi-4-14B-1M-RRP-v1-lora
-- microsoft/phi-4
+license: mit
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: mit
+base_model:
+- prithivMLmods/Phi-4-o1
+- bunnycore/Phi-4-14B-1M-RRP-v1-lora
+- microsoft/phi-4
+model-index:
+- name: Phi4-RP-o1
+  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: 2.2
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
+      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: 51.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
+      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: 36.03
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
+      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: 16.44
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
+      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: 19.18
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
+      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: 45.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -33,4 +128,17 @@ merge_method: passthrough
 models:
   - model: prithivMLmods/Phi-4-o1+bunnycore/Phi-4-14B-1M-RRP-v1-lora
 
-```
+```
+# [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/Triangle104__Phi4-RP-o1-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.52|
+|IFEval (0-Shot)    | 2.20|
+|BBH (3-Shot)       |51.59|
+|MATH Lvl 5 (4-Shot)|36.03|
+|GPQA (0-shot)      |16.44|
+|MuSR (0-shot)      |19.18|
+|MMLU-PRO (5-shot)  |45.67|
+