Adding Evaluation Results

README.md

@@ -1,10 +1,105 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
 tags:
 - chat
+pipeline_tag: text-generation
+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: 58.37
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=natong19/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: 37.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=natong19/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: 10.27
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=natong19/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=natong19/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: 8.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=natong19/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: 31.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=natong19/Qwen2-7B-Instruct-abliterated
+      name: Open LLM Leaderboard
 ---
 
 # Qwen2-7B-Instruct-abliterated
@@ -64,4 +159,17 @@ Evaluation framework: lm-evaluation-harness 0.4.2
 | HellaSwag (10-shot) | 81.8 | 81.7 |
 | MMLU (5-shot) | 70.7 | 70.5 |
 | TruthfulQA (0-shot) | 57.3 | 55.0 |
-| Winogrande (5-shot) | 76.2 | 77.4 |
+| Winogrande (5-shot) | 76.2 | 77.4 |
+# [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_natong19__Qwen2-7B-Instruct-abliterated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.62|
+|IFEval (0-Shot)    |58.37|
+|BBH (3-Shot)       |37.75|
+|MATH Lvl 5 (4-Shot)|10.27|
+|GPQA (0-shot)      | 6.82|
+|MuSR (0-shot)      | 8.93|
+|MMLU-PRO (5-shot)  |31.58|
+