Adding Evaluation Results

README.md

@@ -1,15 +1,109 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - bunnycore/HyperLlama-3.1-8B
 - mlabonne/NeuralDaredevil-8B-abliterated
 - Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
 - mlabonne/Hermes-3-Llama-3.1-8B-lorablated
 - darkc0de/BuddyGlass_v0.2_Xortron7MethedUpSwitchedUp
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp
+  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: 43.58
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp
+      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: 31.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp
+      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: 11.1
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp
+      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: 6.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp
+      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: 9.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp
+      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: 29.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -45,3 +139,17 @@ 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_darkc0de__BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.04|
+|IFEval (0-Shot)    |43.58|
+|BBH (3-Shot)       |31.87|
+|MATH Lvl 5 (4-Shot)|11.10|
+|GPQA (0-shot)      | 6.49|
+|MuSR (0-shot)      | 9.49|
+|MMLU-PRO (5-shot)  |29.70|
+