Adding Evaluation Results (#1)

- Adding Evaluation Results (2e13a442eb83bbe80dc72cd7854b58b0e485c5b5)


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

README.md

@@ -4,6 +4,101 @@ tags:
 - merge
 - mergekit
 - lazymergekit
+model-index:
+- name: HyperLlama-3.1-8B
+ 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: 78.83
+ name: strict accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/HyperLlama-3.1-8B
+ 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: 29.81
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/HyperLlama-3.1-8B
+ 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: 16.01
+ name: exact match
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/HyperLlama-3.1-8B
+ 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: 4.92
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/HyperLlama-3.1-8B
+ 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: 7.93
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/HyperLlama-3.1-8B
+ 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: 30.92
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/HyperLlama-3.1-8B
+ name: Open LLM Leaderboard
 ---
 
 # HyperLlama-3.1-8B
@@ -22,4 +117,17 @@ base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
 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__HyperLlama-3.1-8B)
+
+| Metric |Value|
+|-------------------|----:|
+|Avg. |28.07|
+|IFEval (0-Shot) |78.83|
+|BBH (3-Shot) |29.81|
+|MATH Lvl 5 (4-Shot)|16.01|
+|GPQA (0-shot) | 4.92|
+|MuSR (0-shot) | 7.93|
+|MMLU-PRO (5-shot) |30.92|
+