Adding Evaluation Results

README.md

@@ -1,15 +1,109 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - open-thoughts/OpenThinker-7B
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
 - Qwen/Qwen2.5-7B-Instruct-1M
 - NovaSky-AI/Sky-T1-mini
 - open-r1/OpenR1-Qwen-7B
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Qwen2.5-7B-Sky-R1-Mini
+  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: 23.05
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-Sky-R1-Mini
+      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: 8.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-Sky-R1-Mini
+      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: 2.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-Sky-R1-Mini
+      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: 5.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-Sky-R1-Mini
+      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: 1.27
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-Sky-R1-Mini
+      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: 2.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-Sky-R1-Mini
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -47,3 +141,17 @@ parameters:
   select_topk: 1.0
 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/bunnycore__Qwen2.5-7B-Sky-R1-Mini-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 7.37|
+|IFEval (0-Shot)    |23.05|
+|BBH (3-Shot)       | 8.90|
+|MATH Lvl 5 (4-Shot)| 2.95|
+|GPQA (0-shot)      | 5.26|
+|MuSR (0-shot)      | 1.27|
+|MMLU-PRO (5-shot)  | 2.81|
+