Adding Evaluation Results (#1)

- Adding Evaluation Results (175908063f4d57ccc59e4f38adf96e2051ba49d5)

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- Nexesenex/Llama_3.1_8b_DeepDive_3_R1_Prev_v1.0
-- Nexesenex/Llama_3.1_8b_Smarteaz_0.2_R1
-- SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
+license: llama3.1
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.1
+base_model:
+- Nexesenex/Llama_3.1_8b_DeepDive_3_R1_Prev_v1.0
+- Nexesenex/Llama_3.1_8b_Smarteaz_0.2_R1
+- SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
+model-index:
+- name: Llama_3.1_8b_DobHerWild_R1_v1.1R
+  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: 76.0
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_DobHerWild_R1_v1.1R
+      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: 32.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_DobHerWild_R1_v1.1R
+      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: 23.19
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_DobHerWild_R1_v1.1R
+      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=Nexesenex/Llama_3.1_8b_DobHerWild_R1_v1.1R
+      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: 9.89
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_DobHerWild_R1_v1.1R
+      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: 29.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_DobHerWild_R1_v1.1R
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -40,4 +135,17 @@ models:
 base_model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
 dtype: bfloat16
 normalize: true
-```
+```
+# [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/Nexesenex__Llama_3.1_8b_DobHerWild_R1_v1.1R-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |29.73|
+|IFEval (0-Shot)    |76.00|
+|BBH (3-Shot)       |32.83|
+|MATH Lvl 5 (4-Shot)|23.19|
+|GPQA (0-shot)      | 6.60|
+|MuSR (0-shot)      | 9.89|
+|MMLU-PRO (5-shot)  |29.87|
+