Adding Evaluation Results (#1)

- Adding Evaluation Results (63177e107dabb695d9dc07daf5d378f84c220a82)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- Weyaxi/Einstein-v6.1-Llama3-8B
-- flammenai/Mahou-1.3-llama3-8B
-- Danielbrdz/Barcenas-Llama3-8b-ORPO
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- Weyaxi/Einstein-v6.1-Llama3-8B
+- flammenai/Mahou-1.3-llama3-8B
+- Danielbrdz/Barcenas-Llama3-8b-ORPO
+model-index:
+- name: llama3-8B-V2
+  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: 41.23
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-V2
+      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: 30.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-V2
+      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=Naveenpoliasetty/llama3-8B-V2
+      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: 5.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-V2
+      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: 9.18
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-V2
+      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: 30.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-V2
+      name: Open LLM Leaderboard
 ---
 # merged_model
 
@@ -45,3 +139,17 @@ merge_method: linear
 tokenizer_source: union
 dtype: float16
 ```
+
+# [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_Naveenpoliasetty__llama3-8B-V2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.69|
+|IFEval (0-Shot)    |41.23|
+|BBH (3-Shot)       |30.87|
+|MATH Lvl 5 (4-Shot)| 7.10|
+|GPQA (0-shot)      | 5.37|
+|MuSR (0-shot)      | 9.18|
+|MMLU-PRO (5-shot)  |30.42|
+