Adding Evaluation Results (#1)

- Adding Evaluation Results (a32bb1e9db6b52d68f41eb033eda95dbd9bbb97d)


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

README.md

@@ -2,6 +2,101 @@
 library_name: transformers
 tags:
 - uncensored
+model-index:
+- name: Qwen2-7B-Instruct-abliterated
+  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: 58.22
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=informatiker/Qwen2-7B-Instruct-abliterated
+      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: 37.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=informatiker/Qwen2-7B-Instruct-abliterated
+      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: 8.38
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=informatiker/Qwen2-7B-Instruct-abliterated
+      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: 6.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=informatiker/Qwen2-7B-Instruct-abliterated
+      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: 6.83
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=informatiker/Qwen2-7B-Instruct-abliterated
+      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: 31.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=informatiker/Qwen2-7B-Instruct-abliterated
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -23,4 +118,17 @@ It will mostly not refuse queries, even less with the provided system prompt.
 
 ### Limitations
 
-The abliteration of this model is not perfect, for some extreme prompts it might refuse. v2 coming soon.
+The abliteration of this model is not perfect, for some extreme prompts it might refuse. v2 coming soon.
+# [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_informatiker__Qwen2-7B-Instruct-abliterated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.00|
+|IFEval (0-Shot)    |58.22|
+|BBH (3-Shot)       |37.80|
+|MATH Lvl 5 (4-Shot)| 8.38|
+|GPQA (0-shot)      | 6.82|
+|MuSR (0-shot)      | 6.83|
+|MMLU-PRO (5-shot)  |31.92|
+