Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- huihui-ai/Dria-Agent-a-3B-abliterated
-- huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated
-- huihui-ai/Qwen2.5-3B-Instruct-abliterated
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- huihui-ai/Dria-Agent-a-3B-abliterated
+- huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated
+- huihui-ai/Qwen2.5-3B-Instruct-abliterated
+model-index:
+- name: Qwen_2.5_3b_Smarteaz_0.01a
+  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: 40.12
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a
+      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: 24.37
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a
+      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: 18.05
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a
+      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: 3.69
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a
+      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: 12.87
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a
+      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: 20.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -44,3 +138,17 @@ chat_template: auto
 tokenizer:
   source: union
 ```
+
+# [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/Nexesenex__Qwen_2.5_3b_Smarteaz_0.01a-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.96|
+|IFEval (0-Shot)    |40.12|
+|BBH (3-Shot)       |24.37|
+|MATH Lvl 5 (4-Shot)|18.05|
+|GPQA (0-shot)      | 3.69|
+|MuSR (0-shot)      |12.87|
+|MMLU-PRO (5-shot)  |20.67|
+