Adding Evaluation Results (#1)

- Adding Evaluation Results (a9f63cb78773fb492e7845764ed2558dcfa03090)


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

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- aetherwiing/MN-12B-Starcannon-v3
-- Sao10K/MN-12B-Lyra-v1
 tags:
 - merge
 - mergekit
 - lazymergekit
 - aetherwiing/MN-12B-Starcannon-v3
 - Sao10K/MN-12B-Lyra-v1
+base_model:
+- aetherwiing/MN-12B-Starcannon-v3
+- Sao10K/MN-12B-Lyra-v1
+model-index:
+- name: MN-LooseCannon-12B-v1
+ 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: 54.18
+ name: strict accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
+ 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: 29.98
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
+ 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: 6.5
+ name: exact match
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
+ 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: 4.7
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
+ 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: 10.96
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
+ 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: 24.4
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=GalrionSoftworks/MN-LooseCannon-12B-v1
+ name: Open LLM Leaderboard
 ---
 
 # MN-LooseCannon-12B-v1
@@ -59,4 +154,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_GalrionSoftworks__MN-LooseCannon-12B-v1)
+
+| Metric |Value|
+|-------------------|----:|
+|Avg. |21.78|
+|IFEval (0-Shot) |54.18|
+|BBH (3-Shot) |29.98|
+|MATH Lvl 5 (4-Shot)| 6.50|
+|GPQA (0-shot) | 4.70|
+|MuSR (0-shot) |10.96|
+|MMLU-PRO (5-shot) |24.40|
+