Adding Evaluation Results (#1)

- Adding Evaluation Results (2e5ff8760dde801517fc4fc9385e4438e3f4b5d4)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,11 +1,106 @@
 ---
+tags:
+- mergekit
+- merge
 base_model:
 - Jacoby746/Proto-Harpy-Avian-v0.1-7B
 - Jacoby746/Proto-Harpy-Burst-v0.1-7B
 - Jacoby746/Proto-Harpy-Spark-v0.1-7B
-tags:
-- mergekit
-- merge
+model-index:
+- name: Proto-Harpy-Blazing-Light-v0.1-2x7B
+  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: 49.05
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B
+      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: 32.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B
+      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: 6.34
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B
+      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: 6.04
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B
+      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: 14.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B
+      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: 25.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -22,3 +117,17 @@ The following models were included in the merge:
 * Jacoby746/Proto-Harpy-Avian-v0.1-7B
 * Jacoby746/Proto-Harpy-Burst-v0.1-7B
 * Jacoby746/Proto-Harpy-Spark-v0.1-7B
+
+# [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/details_Jacoby746__Proto-Harpy-Blazing-Light-v0.1-2x7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.29|
+|IFEval (0-Shot)    |49.05|
+|BBH (3-Shot)       |32.63|
+|MATH Lvl 5 (4-Shot)| 6.34|
+|GPQA (0-shot)      | 6.04|
+|MuSR (0-shot)      |14.12|
+|MMLU-PRO (5-shot)  |25.57|
+