Adding Evaluation Results (#4)

- Adding Evaluation Results (f8253381459297be52e9608b9df6c9cde06bf291)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -3,8 +3,6 @@ language:
 - en
 license: other
 library_name: transformers
-license_name: tongyi-qianwen
-license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
 tags:
 - chat
 - qwen
@@ -16,9 +14,106 @@ base_model: Qwen/Qwen2.5-72B
 datasets:
 - argilla/ultrafeedback-binarized-preferences
 model_name: calme-2.2-qwen2.5-72b
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
 pipeline_tag: text-generation
 inference: false
 model_creator: MaziyarPanahi
+model-index:
+- name: calme-2.2-qwen2.5-72b
+  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: 84.77
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2.5-72b
+      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: 61.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2.5-72b
+      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: 3.63
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2.5-72b
+      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: 14.54
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2.5-72b
+      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: 12.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2.5-72b
+      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: 51.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2.5-72b
+      name: Open LLM Leaderboard
 ---
 
 <img src="./calme-2.webp" alt="Calme-2 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -90,4 +185,17 @@ model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.2-qwen2.5-72
 
 # Ethical Considerations
 
-As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
+As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
+# [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_MaziyarPanahi__calme-2.2-qwen2.5-72b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |38.01|
+|IFEval (0-Shot)    |84.77|
+|BBH (3-Shot)       |61.80|
+|MATH Lvl 5 (4-Shot)| 3.63|
+|GPQA (0-shot)      |14.54|
+|MuSR (0-shot)      |12.02|
+|MMLU-PRO (5-shot)  |51.31|
+