Adding Evaluation Results (#4)

- Adding Evaluation Results (225363c4dd319ffec6c58f7994cd6009d415d547)


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

README.md

@@ -22,6 +22,9 @@ model-index:
     - type: inst_level_strict_acc and prompt_level_strict_acc
       value: 78.41
       name: strict accuracy
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 78.14
+      name: strict accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
       name: Open LLM Leaderboard
@@ -37,6 +40,9 @@ model-index:
     - type: acc_norm
       value: 33.29
       name: normalized accuracy
+    - type: acc_norm
+      value: 33.33
+      name: normalized accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
       name: Open LLM Leaderboard
@@ -49,6 +55,9 @@ model-index:
       args:
         num_few_shot: 4
     metrics:
+    - type: exact_match
+      value: 0.0
+      name: exact match
     - type: exact_match
       value: 0.0
       name: exact match
@@ -64,6 +73,9 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
+    - type: acc_norm
+      value: 6.49
+      name: acc_norm
     - type: acc_norm
       value: 6.49
       name: acc_norm
@@ -79,6 +91,9 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
+    - type: acc_norm
+      value: 13.96
+      name: acc_norm
     - type: acc_norm
       value: 13.96
       name: acc_norm
@@ -99,6 +114,9 @@ model-index:
     - type: acc
       value: 34.76
       name: accuracy
+    - type: acc
+      value: 34.66
+      name: accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
       name: Open LLM Leaderboard
@@ -345,3 +363,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MuSR (0-shot)      |13.96|
 |MMLU-PRO (5-shot)  |34.76|
 
+
+# [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_Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.76|
+|IFEval (0-Shot)    |78.14|
+|BBH (3-Shot)       |33.33|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 6.49|
+|MuSR (0-shot)      |13.96|
+|MMLU-PRO (5-shot)  |34.66|
+