Adding Evaluation Results (#8)

- Adding Evaluation Results (0f42ffd322f057c9a39a05a76e60ba0e8dfe1cd9)


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

README.md

@@ -1,23 +1,117 @@
 ---
-license: other
-license_name: tongyi-qianwen
-license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
+license: other
+library_name: transformers
 tags:
 - chat
 - qwen
 - qwen2
 - finetune
 - chatml
-library_name: transformers
+base_model: Qwen/Qwen2-72B-Instruct
+model_name: MaziyarPanahi/Qwen2-72B-Instruct-v0.1
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
 inference: false
 model_creator: MaziyarPanahi
 quantized_by: MaziyarPanahi
-base_model: Qwen/Qwen2-72B-Instruct
-model_name: MaziyarPanahi/Qwen2-72B-Instruct-v0.1
-
+model-index:
+- name: Qwen2-72B-Instruct-v0.1
+  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: 81.63
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-72B-Instruct-v0.1
+      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: 57.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-72B-Instruct-v0.1
+      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: 36.03
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-72B-Instruct-v0.1
+      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: 17.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-72B-Instruct-v0.1
+      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: 20.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-72B-Instruct-v0.1
+      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: 49.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Qwen2-72B-Instruct-v0.1
+      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'"/>
@@ -91,3 +185,17 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Qwen2-72B-Instruct-v0.1")
 model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Qwen2-72B-Instruct-v0.1")
 ```
+
+# [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__Qwen2-72B-Instruct-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |43.61|
+|IFEval (0-Shot)    |81.63|
+|BBH (3-Shot)       |57.33|
+|MATH Lvl 5 (4-Shot)|36.03|
+|GPQA (0-shot)      |17.45|
+|MuSR (0-shot)      |20.15|
+|MMLU-PRO (5-shot)  |49.05|
+