Adding Evaluation Results

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- meditsolutions/Llama-3.1-MedIT-SUN-8B
-- allenai/Llama-3.1-Tulu-3-8B
-- arcee-ai/Llama-3.1-SuperNova-Lite
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- meditsolutions/Llama-3.1-MedIT-SUN-8B
+- allenai/Llama-3.1-Tulu-3-8B
+- arcee-ai/Llama-3.1-SuperNova-Lite
+model-index:
+- name: Tulu-3.1-8B-SuperNova
+  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: 81.94
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Tulu-3.1-8B-SuperNova
+      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: 32.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Tulu-3.1-8B-SuperNova
+      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: 24.32
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Tulu-3.1-8B-SuperNova
+      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: 6.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Tulu-3.1-8B-SuperNova
+      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: 8.69
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Tulu-3.1-8B-SuperNova
+      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: 31.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Tulu-3.1-8B-SuperNova
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -46,3 +140,17 @@ int8_mask: true
 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_bunnycore__Tulu-3.1-8B-SuperNova)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |30.94|
+|IFEval (0-Shot)    |81.94|
+|BBH (3-Shot)       |32.50|
+|MATH Lvl 5 (4-Shot)|24.32|
+|GPQA (0-shot)      | 6.94|
+|MuSR (0-shot)      | 8.69|
+|MMLU-PRO (5-shot)  |31.27|
+