Adding Evaluation Results

README.md

@@ -1,8 +1,8 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
+library_name: transformers
 tags:
 - chat
 - qwen
@@ -13,17 +13,112 @@ tags:
 - HelpSteer2
 - Orca
 - SlimOrca
-library_name: transformers
-inference: false
-model_creator: MaziyarPanahi
-quantized_by: MaziyarPanahi
 base_model: Qwen/Qwen2-7B
-model_name: calme-2.7-qwen2-7b
 datasets:
 - nvidia/HelpSteer2
 - teknium/OpenHermes-2.5
 - microsoft/orca-math-word-problems-200k
 - Open-Orca/SlimOrca
+model_name: calme-2.7-qwen2-7b
+pipeline_tag: text-generation
+inference: false
+model_creator: MaziyarPanahi
+quantized_by: MaziyarPanahi
+model-index:
+- name: calme-2.7-qwen2-7b
+  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: 35.92
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.7-qwen2-7b
+      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: 28.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.7-qwen2-7b
+      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: 12.08
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.7-qwen2-7b
+      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: 5.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.7-qwen2-7b
+      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: 19.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.7-qwen2-7b
+      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: 30.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.7-qwen2-7b
+      name: Open LLM Leaderboard
 ---
 
 <img src="./qwen2-fine-tunes-maziyar-panahi.webp" alt="Qwen2 fine-tune" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -78,4 +173,17 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.7-qwen2-7b")
 model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.7-qwen2-7b")
-```
+```
+# [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-2.7-qwen2-7b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.07|
+|IFEval (0-Shot)    |35.92|
+|BBH (3-Shot)       |28.91|
+|MATH Lvl 5 (4-Shot)|12.08|
+|GPQA (0-shot)      | 5.48|
+|MuSR (0-shot)      |19.94|
+|MMLU-PRO (5-shot)  |30.06|
+