Adding Evaluation Results

README.md

@@ -3,6 +3,101 @@ language:
 - ko
 - en
 license: mit
+model-index:
+- name: free-solar-evo-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: 20.5
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-solar-evo-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: 22.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-solar-evo-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: 0.08
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-solar-evo-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: 5.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-solar-evo-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: 22.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-solar-evo-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: 26.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=freewheelin/free-solar-evo-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for free-solar-evo-v0.1
@@ -13,4 +108,17 @@ license: mit
 - We were inspired by this [Sakana project](https://sakana.ai/evolutionary-model-merge/)
 
 ## Base Model 
-- [hwkwon/S-SOLAR-10.7B-v1.5](https://huggingface.co/hwkwon/S-SOLAR-10.7B-v1.5)
+- [hwkwon/S-SOLAR-10.7B-v1.5](https://huggingface.co/hwkwon/S-SOLAR-10.7B-v1.5)
+# [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-solar-evo-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |16.30|
+|IFEval (0-Shot)    |20.50|
+|BBH (3-Shot)       |22.64|
+|MATH Lvl 5 (4-Shot)| 0.08|
+|GPQA (0-shot)      | 5.48|
+|MuSR (0-shot)      |22.26|
+|MMLU-PRO (5-shot)  |26.82|
+