Adding Evaluation Results (#1)

- Adding Evaluation Results (6662cd774db65f6901178669f6c932a94fc5cf6e)


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

README.md

@@ -1,10 +1,104 @@
 ---
-base_model: []
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model: []
+model-index:
+- name: L3-Stheno-v3.2-12.2B-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: 40.28
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-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: 27.37
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-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: 4.98
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-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: 3.36
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-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: 10.31
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-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: 26.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-Instruct
+      name: Open LLM Leaderboard
 ---
 
 <h2>L3-Stheno-v3.2-12.2B-Instruct - Float32</h2>
@@ -91,3 +185,17 @@ 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-Stheno-v3.2-12.2B-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.73|
+|IFEval (0-Shot)    |40.28|
+|BBH (3-Shot)       |27.37|
+|MATH Lvl 5 (4-Shot)| 4.98|
+|GPQA (0-shot)      | 3.36|
+|MuSR (0-shot)      |10.31|
+|MMLU-PRO (5-shot)  |26.06|
+