Adding Evaluation Results

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- DreadPoor/Heart_Stolen1.1-8B-Model_Stock
-- DreadPoor/Spei_Meridiem-8B-model_stock
-- DreadPoor/Aspire1.1-8B-model_stock
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- DreadPoor/Heart_Stolen1.1-8B-Model_Stock
+- DreadPoor/Spei_Meridiem-8B-model_stock
+- DreadPoor/Aspire1.1-8B-model_stock
+model-index:
+- name: Promissum_Mane-8B-LINEAR
+ 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: 71.5
+ name: strict accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Promissum_Mane-8B-LINEAR
+ 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: 35.25
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Promissum_Mane-8B-LINEAR
+ 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: 13.67
+ name: exact match
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Promissum_Mane-8B-LINEAR
+ 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: 7.27
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Promissum_Mane-8B-LINEAR
+ 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: 13.34
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Promissum_Mane-8B-LINEAR
+ 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: 31.67
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Promissum_Mane-8B-LINEAR
+ name: Open LLM Leaderboard
 ---
 # merge
 
@@ -45,3 +139,17 @@ normalize: false
 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_DreadPoor__Promissum_Mane-8B-LINEAR)
+
+| Metric |Value|
+|-------------------|----:|
+|Avg. |28.78|
+|IFEval (0-Shot) |71.50|
+|BBH (3-Shot) |35.25|
+|MATH Lvl 5 (4-Shot)|13.67|
+|GPQA (0-shot) | 7.27|
+|MuSR (0-shot) |13.34|
+|MMLU-PRO (5-shot) |31.67|
+