Adding Evaluation Results (#1)

- Adding Evaluation Results (983427bb54333b17dc70cd25c6355ea9b4844bc3)


Co-authored-by: Non applicable <CombinHorizon@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,107 @@
 ---
-base_model:
-- DreadPoor/Aurora_faustus-8B-LINEAR
-- grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- DreadPoor/Aurora_faustus-8B-LINEAR
+- grimjim/Llama-3-Instruct-abliteration-LoRA-8B
+model-index:
+- name: Aurora_faustus-8B-LORABLATED
+  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: 75.27
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aurora_faustus-8B-LORABLATED
+      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: 34.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aurora_faustus-8B-LORABLATED
+      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: 12.92
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aurora_faustus-8B-LORABLATED
+      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: 6.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aurora_faustus-8B-LORABLATED
+      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: 13.78
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aurora_faustus-8B-LORABLATED
+      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=DreadPoor/Aurora_faustus-8B-LORABLATED
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -39,4 +134,17 @@ slices:
     parameters:
       weight: 1.0
 
-```
+```
+# [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_DreadPoor__Aurora_faustus-8B-LORABLATED)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.80|
+|IFEval (0-Shot)    |75.27|
+|BBH (3-Shot)       |34.20|
+|MATH Lvl 5 (4-Shot)|12.92|
+|GPQA (0-shot)      | 6.94|
+|MuSR (0-shot)      |13.78|
+|MMLU-PRO (5-shot)  |29.70|
+