Adding Evaluation Results

README.md

@@ -1,4 +1,9 @@
 ---
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - refuelai/Llama-3-Refueled
 - cognitivecomputations/dolphin-2.9-llama3-8b
@@ -6,11 +11,101 @@ base_model:
 - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
 - Sao10K/L3-8B-Stheno-v3.2
 - cgato/L3-TheSpice-8b-v0.8.3
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: apache-2.0
+model-index:
+- name: ONeil-model_stock-8B
+  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: 67.86
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/ONeil-model_stock-8B
+      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: 36.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/ONeil-model_stock-8B
+      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: 9.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/ONeil-model_stock-8B
+      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: 7.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/ONeil-model_stock-8B
+      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: 10.97
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/ONeil-model_stock-8B
+      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: 28.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/ONeil-model_stock-8B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -46,4 +141,17 @@ base_model: Sao10K/L3-8B-Stheno-v3.2
 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__ONeil-model_stock-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.78|
+|IFEval (0-Shot)    |67.86|
+|BBH (3-Shot)       |36.41|
+|MATH Lvl 5 (4-Shot)| 9.21|
+|GPQA (0-shot)      | 7.38|
+|MuSR (0-shot)      |10.97|
+|MMLU-PRO (5-shot)  |28.87|
+