Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -51,7 +51,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 78.00
+      value: 78.0
       name: accuracy
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
@@ -106,6 +106,98 @@ model-index:
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
       name: Open LLM Leaderboard
+  - 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: 53.31
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      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: 45.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      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: 16.24
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      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: 14.21
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      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: 20.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      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: 43.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-evo-qwen72b-v0.8-re
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for free-evo-qwen72b-v0.8
@@ -144,4 +236,17 @@ You can create a framework to automate this process.
 - QWEN2
 
 ## Base Models
-- several QWEN2 based models
+- several QWEN2 based models
+# [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_freewheelin__free-evo-qwen72b-v0.8-re)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |32.17|
+|IFEval (0-Shot)    |53.31|
+|BBH (3-Shot)       |45.32|
+|MATH Lvl 5 (4-Shot)|16.24|
+|GPQA (0-shot)      |14.21|
+|MuSR (0-shot)      |20.96|
+|MMLU-PRO (5-shot)  |43.00|
+