Adding Evaluation Results

README.md

@@ -1,15 +1,109 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - rityak/L3.1-FormaxGradient
 - vicgalle/Configurable-Llama-3.1-8B-Instruct
 - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
 - grimjim/Llama-3-Instruct-abliteration-LoRA-8B
 - DreadPoor/Heart_Stolen-8B-Model_Stock
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: L3.1-ForStHS
+  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: 78.13
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
+      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: 31.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
+      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: 12.92
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
+      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=djuna/L3.1-ForStHS
+      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: 9.66
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
+      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: 30.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -40,3 +134,17 @@ merge_method: model_stock
 base_model: vicgalle/Configurable-Llama-3.1-8B-Instruct
 dtype: bfloat16
 ```
+
+# [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_djuna__L3.1-ForStHS)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.00|
+|IFEval (0-Shot)    |78.13|
+|BBH (3-Shot)       |31.39|
+|MATH Lvl 5 (4-Shot)|12.92|
+|GPQA (0-shot)      | 5.48|
+|MuSR (0-shot)      | 9.66|
+|MMLU-PRO (5-shot)  |30.39|
+