Adding Evaluation Results (#1)

- Adding Evaluation Results (c2314fd67f35c8f00c04bb66dd76be92a83d3c53)


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

README.md

@@ -1,12 +1,107 @@
 ---
-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
 tags:
 - chat
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: Smaug-Qwen2-72B-Instruct
+  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: 78.25
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Qwen2-72B-Instruct
+      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: 56.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Qwen2-72B-Instruct
+      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: 35.35
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Qwen2-72B-Instruct
+      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: 14.88
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Qwen2-72B-Instruct
+      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: 15.18
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Qwen2-72B-Instruct
+      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: 46.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Qwen2-72B-Instruct
+      name: Open LLM Leaderboard
 ---
 
 # Smaug-Qwen2-72B-Instruct
@@ -202,3 +297,17 @@ Average
 |--------------------------|---------|
 | Qwen2-72B-Instruct       | 8.96541 |
 | Smaug-Qwen2-72B-Instruct | 8.86563 |
+
+# [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_abacusai__Smaug-Qwen2-72B-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |41.08|
+|IFEval (0-Shot)    |78.25|
+|BBH (3-Shot)       |56.27|
+|MATH Lvl 5 (4-Shot)|35.35|
+|GPQA (0-shot)      |14.88|
+|MuSR (0-shot)      |15.18|
+|MMLU-PRO (5-shot)  |46.56|
+