Adding Evaluation Results

README.md

@@ -1,12 +1,107 @@
 ---
-license: mit
-datasets:
-- Magpie-Align/Magpie-Pro-300K-Filtered
 language:
 - en
+license: mit
+library_name: transformers
 base_model:
 - Qwen/Qwen2.5-32B-Instruct
-library_name: transformers
+datasets:
+- Magpie-Align/Magpie-Pro-300K-Filtered
+model-index:
+- name: TheBeagle-v2beta-32B-MGS
+  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: 45.03
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/TheBeagle-v2beta-32B-MGS
+      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: 58.07
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/TheBeagle-v2beta-32B-MGS
+      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: 39.43
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/TheBeagle-v2beta-32B-MGS
+      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: 20.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/TheBeagle-v2beta-32B-MGS
+      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: 24.5
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/TheBeagle-v2beta-32B-MGS
+      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: 54.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/TheBeagle-v2beta-32B-MGS
+      name: Open LLM Leaderboard
 ---
 
 # TheBeagle-v2beta-32B-MGS
@@ -87,4 +182,17 @@ We'll see them soon, keep tuned :)
 ## Thanks
 - Qwen Team for their outstanding model
 - MagPie Team for contributing plenty of datasets
-- Cybertron Cloud Compute
+- Cybertron Cloud Compute
+# [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_fblgit__TheBeagle-v2beta-32B-MGS)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |40.29|
+|IFEval (0-Shot)    |45.03|
+|BBH (3-Shot)       |58.07|
+|MATH Lvl 5 (4-Shot)|39.43|
+|GPQA (0-shot)      |20.13|
+|MuSR (0-shot)      |24.50|
+|MMLU-PRO (5-shot)  |54.57|
+