Adding Evaluation Results (#3)

- Adding Evaluation Results (2611afea36acb2288320b1e0bbceb35a31a9784d)

README.md

@@ -24,6 +24,105 @@ datasets:
 - amphora/QwQ-LongCoT-130K
 base_model:
 - microsoft/phi-4
+model-index:
+- name: SuperThoughts-CoT-14B-16k-o1-QwQ
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 5.15
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 52.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 40.79
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 19.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
+      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: 21.79
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
+      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: 47.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
+      name: Open LLM Leaderboard
 ---
 
 gguf/final version: https://huggingface.co/Pinkstack/PARM-V2-phi-4-16k-CoT-o1-gguf
@@ -75,4 +174,18 @@ All generated locally and pretty quickly too! 😲 Due to our very limited resou
 - **License:** MIT
 - **Finetuned from model :** microsoft/phi-4
 
-This phi-4 model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+This phi-4 model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+# [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/Pinkstack__SuperThoughts-CoT-14B-16k-o1-QwQ-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    31.17|
+|IFEval (0-Shot)    |     5.15|
+|BBH (3-Shot)       |    52.85|
+|MATH Lvl 5 (4-Shot)|    40.79|
+|GPQA (0-shot)      |    19.02|
+|MuSR (0-shot)      |    21.79|
+|MMLU-PRO (5-shot)  |    47.43|
+