Adding Evaluation Results

README.md

@@ -1,14 +1,108 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - LeroyDyer/_Spydaz_Web_AI_AGI_R1_OmG_Coder
 - LeroyDyer/_Spydaz_Web_AI_AGI_R1_Math_AdvancedStudent
 - LeroyDyer/LCARS_TOP_SCORE
 - LeroyDyer/_Spydaz_Web_AI_AGI_R1_Math_001
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: _Spydaz_Web_AI_AGI_R1_Top_Student
+  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: 60.4
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
+      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: 29.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
+      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: 7.25
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
+      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: 3.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
+      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: 29.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
+      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: 22.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
+      name: Open LLM Leaderboard
 ---
 Rank 1588 - TOP MISTRAL 7B
 # Winners create more winners, while losers do the opposite.
@@ -64,3 +158,17 @@ Turing's test evaluates AI by its ability to mimic human behavior convincingly,
 
 Russell and Norvig advocate for AI that acts rationally to achieve the best outcomes, integrating reasoning and adaptability to environments.
 
+
+# [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/LeroyDyer___Spydaz_Web_AI_AGI_R1_Top_Student-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.31|
+|IFEval (0-Shot)    |60.40|
+|BBH (3-Shot)       |29.31|
+|MATH Lvl 5 (4-Shot)| 7.25|
+|GPQA (0-shot)      | 3.02|
+|MuSR (0-shot)      |29.37|
+|MMLU-PRO (5-shot)  |22.49|
+