Adding Evaluation Results (#1)

- Adding Evaluation Results (0337cc48f97c9cc67b27679897c4af28a93094ae)

README.md

@@ -1,16 +1,111 @@
 ---
-base_model:
-- bunnycore/Phi-4-RR-Shoup
-- bunnycore/Phi-4-Model-Stock-v4
+language:
+- en
+license: mit
 library_name: transformers
 tags:
 - mergekit
 - merge
 - phi-4
-license: mit
-language:
-- en
+base_model:
+- bunnycore/Phi-4-RR-Shoup
+- bunnycore/Phi-4-Model-Stock-v4
 pipeline_tag: text-generation
+model-index:
+- name: Luminis-phi-4
+  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: 69.0
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Luminis-phi-4
+      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: 55.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Luminis-phi-4
+      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: 43.66
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Luminis-phi-4
+      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: 13.53
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Luminis-phi-4
+      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: 16.68
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Luminis-phi-4
+      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: 49.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Luminis-phi-4
+      name: Open LLM Leaderboard
 ---
 # merged
 
@@ -48,4 +143,17 @@ slices:
     model: bunnycore/Phi-4-Model-Stock-v4
   - layer_range: [0, 40]
     model: bunnycore/Phi-4-RR-Shoup
-```
+```
+# [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/suayptalha__Luminis-phi-4-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |41.30|
+|IFEval (0-Shot)    |69.00|
+|BBH (3-Shot)       |55.80|
+|MATH Lvl 5 (4-Shot)|43.66|
+|GPQA (0-shot)      |13.53|
+|MuSR (0-shot)      |16.68|
+|MMLU-PRO (5-shot)  |49.15|
+