Adding Evaluation Results (#2)

- Adding Evaluation Results (48f7c352a0dd67103d530299f1fd7d1b3e7d1f0f)


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

README.md

@@ -1,15 +1,110 @@
 ---
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - openlynn/Llama-3-Soliloquy-8B-v2
 - grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
 - grimjim/llama-3-aaditya-OpenBioLLM-8B
 - grimjim/llama-3-Nephilim-v1-8B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: cc-by-nc-4.0
 pipeline_tag: text-generation
+model-index:
+- name: llama-3-Nephilim-v2-8B
+ 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: 39.22
+ name: strict accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v2-8B
+ 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: 29.9
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v2-8B
+ 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: 9.52
+ name: exact match
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v2-8B
+ 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: 6.6
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v2-8B
+ 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: 7.89
+ name: acc_norm
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v2-8B
+ 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: 29.35
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v2-8B
+ name: Open LLM Leaderboard
 ---
 # llama-3-Nephilim-v2-8B
 
@@ -70,3 +165,17 @@ slices:
  weight: 0.1
 
 ```
+
+# [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_grimjim__llama-3-Nephilim-v2-8B)
+
+| Metric |Value|
+|-------------------|----:|
+|Avg. |20.41|
+|IFEval (0-Shot) |39.22|
+|BBH (3-Shot) |29.90|
+|MATH Lvl 5 (4-Shot)| 9.52|
+|GPQA (0-shot) | 6.60|
+|MuSR (0-shot) | 7.89|
+|MMLU-PRO (5-shot) |29.35|
+