Adding Evaluation Results (#1)

- Adding Evaluation Results (34281d49593b77e0fdf08977c9f70e8f528adb3b)


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

README.md

@@ -1,4 +1,9 @@
 ---
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - akjindal53244/Llama-3.1-Storm-8B
 - ResplendentAI/NoWarning_Llama3
@@ -12,11 +17,101 @@ base_model:
 - kloodia/lora-8b-medic
 - mlabonne/Hermes-3-Llama-3.1-8B-lorablated
 - kloodia/lora-8b-bio
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: apache-2.0
+model-index:
+- name: Heart_Stolen-8B-Model_Stock
+  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: 72.45
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock
+      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: 34.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock
+      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: 14.65
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock
+      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: 8.95
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-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: 12.36
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-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: 31.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -52,4 +147,17 @@ base_model: Sao10K/L3-8B-Stheno-v3.2+ResplendentAI/Smarts_Llama3
 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/details_DreadPoor__Heart_Stolen-8B-Model_Stock)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.98|
+|IFEval (0-Shot)    |72.45|
+|BBH (3-Shot)       |34.44|
+|MATH Lvl 5 (4-Shot)|14.65|
+|GPQA (0-shot)      | 8.95|
+|MuSR (0-shot)      |12.36|
+|MMLU-PRO (5-shot)  |31.04|
+