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

@@ -1,4 +1,9 @@
 ---
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
 - VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
@@ -6,11 +11,101 @@ base_model:
 - nbeerbower/llama-3-gutenberg-8B
 - jpacifico/French-Alpaca-Llama3-8B-Instruct-v1.0
 - meta-llama/Meta-Llama-3-8B-Instruct
-library_name: transformers
-license: apache-2.0
-tags:
-- mergekit
-- merge
+model-index:
+- name: Llama-3-8B-Instruct_ties-density-0.1
+  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: 41.16
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=johnsutor/Llama-3-8B-Instruct_ties-density-0.1
+      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: 28.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=johnsutor/Llama-3-8B-Instruct_ties-density-0.1
+      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: 7.1
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=johnsutor/Llama-3-8B-Instruct_ties-density-0.1
+      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: 5.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=johnsutor/Llama-3-8B-Instruct_ties-density-0.1
+      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: 10.67
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=johnsutor/Llama-3-8B-Instruct_ties-density-0.1
+      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: 28.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=johnsutor/Llama-3-8B-Instruct_ties-density-0.1
+      name: Open LLM Leaderboard
 ---
 # Model Merge Parameters
 Base model: meta-llama/Meta-Llama-3-8B-Instruct
@@ -26,3 +121,17 @@ density: 0.1
 normalize: true
 weight: 1.0
 
+
+# [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_johnsutor__Llama-3-8B-Instruct_ties-density-0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.29|
+|IFEval (0-Shot)    |41.16|
+|BBH (3-Shot)       |28.77|
+|MATH Lvl 5 (4-Shot)| 7.10|
+|GPQA (0-shot)      | 5.15|
+|MuSR (0-shot)      |10.67|
+|MMLU-PRO (5-shot)  |28.89|
+