Adding Evaluation Results

README.md

@@ -1,22 +1,117 @@
 ---
-license: other
-license_name: qwen
-license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
+license: other
+library_name: transformers
 tags:
 - chat
 - qwen
 - qwen2.5
 - finetune
 - english
-library_name: transformers
+base_model: MaziyarPanahi/calme-3-selfmerge-qwen2-78b
+model_name: calme-3.1-instruct-78b
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
 inference: false
 model_creator: MaziyarPanahi
 quantized_by: MaziyarPanahi
-base_model: MaziyarPanahi/calme-3-selfmerge-qwen2-78b
-model_name: calme-3.1-instruct-78b
+model-index:
+- name: calme-3.1-instruct-78b
+  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: 81.36
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.1-instruct-78b
+      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: 62.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.1-instruct-78b
+      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: 38.75
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.1-instruct-78b
+      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: 19.46
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.1-instruct-78b
+      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: 36.5
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.1-instruct-78b
+      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: 68.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.1-instruct-78b
+      name: Open LLM Leaderboard
 ---
 
 <img src="./calme_3.png" alt="Calme-3 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -77,3 +172,17 @@ model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.1-instruct-7
 # 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.
+
+# [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-3.1-instruct-78b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |51.20|
+|IFEval (0-Shot)    |81.36|
+|BBH (3-Shot)       |62.41|
+|MATH Lvl 5 (4-Shot)|38.75|
+|GPQA (0-shot)      |19.46|
+|MuSR (0-shot)      |36.50|
+|MMLU-PRO (5-shot)  |68.72|
+