Adding Evaluation Results (#1)

- Adding Evaluation Results (34e08e68126f49d4c1e7f222a730a7bf18a9a3ba)

README.md

@@ -9,6 +9,105 @@ base_model:
 tags:
 - merge
 - mergekit
+model-index:
+- name: Llama3.1-Daredevilish-Instruct
+  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: 79.41
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-Daredevilish-Instruct
+      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: 32.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-Daredevilish-Instruct
+      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: 16.77
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-Daredevilish-Instruct
+      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: 7.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-Daredevilish-Instruct
+      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: 7.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-Daredevilish-Instruct
+      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: 31.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-Daredevilish-Instruct
+      name: Open LLM Leaderboard
 ---
 # Llama 3.1 Daredevilish Instruct
 
@@ -55,4 +154,18 @@ This experimental model is designed for research and development purposes. Users
 
 ## Future Work
 
-Further evaluation and fine-tuning may be necessary to optimize performance across various tasks. Researchers are encouraged to build upon this experimental merge to advance the capabilities of Llama-based models.
+Further evaluation and fine-tuning may be necessary to optimize performance across various tasks. Researchers are encouraged to build upon this experimental merge to advance the capabilities of Llama-based models.
+# [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/agentlans__Llama3.1-Daredevilish-Instruct-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=agentlans%2FLlama3.1-Daredevilish-Instruct&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    29.32|
+|IFEval (0-Shot)    |    79.41|
+|BBH (3-Shot)       |    32.22|
+|MATH Lvl 5 (4-Shot)|    16.77|
+|GPQA (0-shot)      |     7.61|
+|MuSR (0-shot)      |     7.92|
+|MMLU-PRO (5-shot)  |    31.97|
+