Adding Evaluation Results

README.md

@@ -1,14 +1,109 @@
 ---
-license: other
-license_name: qwen
-base_model: Qwen/Qwen2.5-Math-72B
-license_link: https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
+license: other
+library_name: transformers
 tags:
 - chat
-library_name: transformers
+base_model: Qwen/Qwen2.5-Math-72B
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: Qwen2.5-Math-72B-Instruct
+ 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: 40.03
+ name: strict accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-Math-72B-Instruct
+ 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: 48.97
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-Math-72B-Instruct
+ 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: 18.5
+ name: exact match
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-Math-72B-Instruct
+ 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: 10.85
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-Math-72B-Instruct
+ 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: 16.34
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-Math-72B-Instruct
+ 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: 42.36
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Qwen/Qwen2.5-Math-72B-Instruct
+ name: Open LLM Leaderboard
 ---
 
 
@@ -118,4 +213,17 @@ If you find our work helpful, feel free to give us a citation.
  journal={arXiv preprint arXiv:2409.12122},
  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-Math-72B-Instruct)
+
+| Metric |Value|
+|-------------------|----:|
+|Avg. |29.51|
+|IFEval (0-Shot) |40.03|
+|BBH (3-Shot) |48.97|
+|MATH Lvl 5 (4-Shot)|18.50|
+|GPQA (0-shot) |10.85|
+|MuSR (0-shot) |16.34|
+|MMLU-PRO (5-shot) |42.36|
+