Adding Evaluation Results

README.md

@@ -1,15 +1,110 @@
 ---
-library_name: transformers
-license: apache-2.0
-license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
-base_model: Qwen/Qwen2.5-7B-Instruct
+license: apache-2.0
+library_name: transformers
 tags:
 - chat
 - abliterated
 - uncensored
+base_model: Qwen/Qwen2.5-7B-Instruct
+license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: Qwen2.5-7B-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: 75.46
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-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: 32.89
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-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: 8.72
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-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: 7.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-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: 35.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      name: Open LLM Leaderboard
 ---
 
 # huihui-ai/Qwen2.5-7B-Instruct-abliterated
@@ -109,3 +204,17 @@ The following data has been re-evaluated and calculated as the average for each
 
 The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/eval.sh)
 
+
+# [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_huihui-ai__Qwen2.5-7B-Instruct-abliterated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.65|
+|IFEval (0-Shot)    |75.46|
+|BBH (3-Shot)       |32.89|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 8.72|
+|MuSR (0-shot)      | 7.48|
+|MMLU-PRO (5-shot)  |35.33|
+