Adding Evaluation Results

README.md

@@ -1,9 +1,104 @@
 ---
-license: apache-2.0
-license_link: https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE
 language:
 - en
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE
 pipeline_tag: text-generation
+model-index:
+- name: Qwen2.5-32B
+  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: 40.77
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-32B
+      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: 53.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-32B
+      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: 32.85
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-32B
+      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: 21.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-32B
+      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: 22.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-32B
+      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: 53.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-32B
+      name: Open LLM Leaderboard
 ---
 
 # Qwen2.5-32B
@@ -65,4 +160,17 @@ If you find our work helpful, feel free to give us a cite.
       journal={arXiv preprint arXiv:2407.10671},
       year={2024}
 }
-```
+```
+# [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_Qwen__Qwen2.5-32B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |37.54|
+|IFEval (0-Shot)    |40.77|
+|BBH (3-Shot)       |53.95|
+|MATH Lvl 5 (4-Shot)|32.85|
+|GPQA (0-shot)      |21.59|
+|MuSR (0-shot)      |22.70|
+|MMLU-PRO (5-shot)  |53.39|
+