Adding Evaluation Results (#1)

- Adding Evaluation Results (fc5295452ee2070411d2f92f0413fabec0bfbb36)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,4 +1,9 @@
 ---
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
 - kloodia/lora-8b-bio
@@ -12,11 +17,101 @@ base_model:
 - kloodia/lora-8b-physic
 - aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
 - kloodia/lora-8b-medic
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: apache-2.0
+model-index:
+- name: Aspire-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: 71.41
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 32.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 12.99
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 8.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 13.46
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 30.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-8B-model_stock
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -56,3 +151,17 @@ dtype: bfloat16
 ```
 
 ![image.png](https://cdn-uploads.huggingface.co/production/uploads/632149f88c0da827c72dccde/IkTIiq6HjCkaJefSNtGLD.png)
+
+# [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__Aspire-8B-model_stock)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.28|
+|IFEval (0-Shot)    |71.41|
+|BBH (3-Shot)       |32.53|
+|MATH Lvl 5 (4-Shot)|12.99|
+|GPQA (0-shot)      | 8.61|
+|MuSR (0-shot)      |13.46|
+|MMLU-PRO (5-shot)  |30.70|
+