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

@@ -1,10 +1,104 @@
 ---
-base_model: []
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model: []
+model-index:
+- name: L3-Lumimaid-12.2B-v0.1-OAS-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: 39.24
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-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: 24.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-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: 3.85
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-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: 3.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-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: 11.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-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: 23.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct
+      name: Open LLM Leaderboard
 ---
 # L3-Lumimaid-12.2B-v0.1-OAS-Instruct - Float32
 
@@ -90,3 +184,17 @@ slices:
 merge_method: passthrough
 dtype: float32
 ```
+
+# [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_DavidAU__L3-Lumimaid-12.2B-v0.1-OAS-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.71|
+|IFEval (0-Shot)    |39.24|
+|BBH (3-Shot)       |24.50|
+|MATH Lvl 5 (4-Shot)| 3.85|
+|GPQA (0-shot)      | 3.58|
+|MuSR (0-shot)      |11.26|
+|MMLU-PRO (5-shot)  |23.80|
+