Adding Evaluation Results (#1)

- Adding Evaluation Results (96e66e5717a12527162350b0fc45b5086a920a7f)


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

README.md

@@ -1,8 +1,7 @@
 ---
-base_model:
-- yuvraj17/Llama-3-8B-spectrum-25
-- ruggsea/Llama3-stanford-encyclopedia-philosophy-QA
-- arcee-ai/Llama-3.1-SuperNova-Lite
+language:
+- en
+license: apache-2.0
 tags:
 - merge
 - mergekit
@@ -10,10 +9,106 @@ tags:
 - yuvraj17/Llama-3-8B-spectrum-25
 - ruggsea/Llama3-stanford-encyclopedia-philosophy-QA
 - arcee-ai/Llama-3.1-SuperNova-Lite
-license: apache-2.0
-language:
-- en
+base_model:
+- yuvraj17/Llama-3-8B-spectrum-25
+- ruggsea/Llama3-stanford-encyclopedia-philosophy-QA
+- arcee-ai/Llama-3.1-SuperNova-Lite
 pipeline_tag: text-generation
+model-index:
+- name: Llama3-8B-SuperNova-Spectrum-dare_ties
+  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: 40.13
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=yuvraj17/Llama3-8B-SuperNova-Spectrum-dare_ties
+      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: 23.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=yuvraj17/Llama3-8B-SuperNova-Spectrum-dare_ties
+      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: 7.4
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=yuvraj17/Llama3-8B-SuperNova-Spectrum-dare_ties
+      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=yuvraj17/Llama3-8B-SuperNova-Spectrum-dare_ties
+      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: 11.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=yuvraj17/Llama3-8B-SuperNova-Spectrum-dare_ties
+      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: 28.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=yuvraj17/Llama3-8B-SuperNova-Spectrum-dare_ties
+      name: Open LLM Leaderboard
 ---
 
 # Llama3-8B-SuperNova-Spectrum-dare_ties
@@ -180,4 +275,17 @@ Average: 43.91%
 
 ## Special thanks & Reference
 - Maxime Labonne for their easy-to-use colab-notebook [Merging LLMs with MergeKit](https://github.com/mlabonne/llm-course/blob/main/Mergekit.ipynb), [Blog](https://towardsdatascience.com/merge-large-language-models-with-mergekit-2118fb392b54) and [LLM-AutoEva Notebookl](https://github.com/mlabonne/llm-autoeval)
-- Authors of [Mergekit](https://github.com/arcee-ai/mergekit)
+- Authors of [Mergekit](https://github.com/arcee-ai/mergekit)
+# [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_yuvraj17__Llama3-8B-SuperNova-Spectrum-dare_ties)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.00|
+|IFEval (0-Shot)    |40.13|
+|BBH (3-Shot)       |23.49|
+|MATH Lvl 5 (4-Shot)| 7.40|
+|GPQA (0-shot)      | 3.36|
+|MuSR (0-shot)      |11.00|
+|MMLU-PRO (5-shot)  |28.60|
+