Adding Evaluation Results (#5)

- Adding Evaluation Results (f90500be9bfccfede04eafb261030193ce38b4f5)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,11 +1,9 @@
 ---
-license: other
-license_name: qwen-research
-license_link: https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE
 language:
 - fr
 - en
-pipeline_tag: text-generation
+license: other
+library_name: transformers
 tags:
 - chat
 - qwen
@@ -13,15 +11,112 @@ tags:
 - finetune
 - french
 - english
-library_name: transformers
-inference: false
-model_creator: MaziyarPanahi
-quantized_by: MaziyarPanahi
 base_model: Qwen/Qwen2.5-3B
-model_name: calme-3.2-instruct-3b
 datasets:
 - MaziyarPanahi/french_instruct_sharegpt
 - arcee-ai/EvolKit-20k
+model_name: calme-3.2-instruct-3b
+license_name: qwen-research
+license_link: https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE
+pipeline_tag: text-generation
+inference: false
+model_creator: MaziyarPanahi
+quantized_by: MaziyarPanahi
+model-index:
+- name: calme-3.2-instruct-3b
+  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: 55.33
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-3b
+      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: 27.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-3b
+      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: 9.89
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-3b
+      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: 4.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-3b
+      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: 8.79
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-3b
+      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: 29.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-3b
+      name: Open LLM Leaderboard
 ---
 
 <img src="./calme_3.png" alt="Calme-3 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -87,4 +182,17 @@ model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.2-instruct-3
 
 # 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-3.2-instruct-3b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.66|
+|IFEval (0-Shot)    |55.33|
+|BBH (3-Shot)       |27.98|
+|MATH Lvl 5 (4-Shot)| 9.89|
+|GPQA (0-shot)      | 4.47|
+|MuSR (0-shot)      | 8.79|
+|MMLU-PRO (5-shot)  |29.48|
+