Adding Evaluation Results (#3)

- Adding Evaluation Results (dc117076342c45f8fd8517f1ecc29aff45f5aac8)


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

README.md

@@ -8,6 +8,101 @@ tags:
 base_model: Qwen/Qwen2.5-14B-Instruct
 license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE
 pipeline_tag: text-generation
+model-index:
+- name: Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
+  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: 82.92
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
+      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: 48.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
+      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: 12.3
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
+      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: 13.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
+      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: 44.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
+      name: Open LLM Leaderboard
 ---
 
 
@@ -252,4 +347,17 @@ If you find our work helpful, feel free to give us a cite.
       journal={arXiv preprint arXiv:2407.10671},
       year={2024}
 }
-```
+```
+# [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-Qwen2.5-14B-Instruct-abliterated-v4)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |33.51|
+|IFEval (0-Shot)    |82.92|
+|BBH (3-Shot)       |48.05|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      |12.30|
+|MuSR (0-shot)      |13.15|
+|MMLU-PRO (5-shot)  |44.65|
+