Adding Evaluation Results (#1)

- Adding Evaluation Results (593fc555723c9e578331cabd74cc42bf199cdfec)

README.md

@@ -17,6 +17,105 @@ tags:
 - mergekit
 - merge
 license: llama3.1
+model-index:
+- name: Wannabe-8B-Model_Stock
+  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: 72.05
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=DreadPoor%2FWannabe-8B-Model_Stock
+      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: 34.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=DreadPoor%2FWannabe-8B-Model_Stock
+      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: 17.6
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=DreadPoor%2FWannabe-8B-Model_Stock
+      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: 6.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=DreadPoor%2FWannabe-8B-Model_Stock
+      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: 12.32
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=DreadPoor%2FWannabe-8B-Model_Stock
+      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: 31.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=DreadPoor%2FWannabe-8B-Model_Stock
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -53,4 +152,18 @@ normalize: false
 int8_mask: true
 dtype: bfloat16
 
-```
+```
+# [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/DreadPoor__Wannabe-8B-Model_Stock-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=DreadPoor%2FWannabe-8B-Model_Stock&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    29.09|
+|IFEval (0-Shot)    |    72.05|
+|BBH (3-Shot)       |    34.28|
+|MATH Lvl 5 (4-Shot)|    17.60|
+|GPQA (0-shot)      |     6.82|
+|MuSR (0-shot)      |    12.32|
+|MMLU-PRO (5-shot)  |    31.45|
+