Adding Evaluation Results

README.md

@@ -1,11 +1,8 @@
 ---
-base_model: mistralai/Mistral-Small-Instruct-2409
-license: other
-license_name: mrl
-license_link: https://mistral.ai/licenses/MRL-0.1.md
-pipeline_tag: text-generation
 language:
 - en
+license: other
+library_name: transformers
 tags:
 - llm
 - mistral
@@ -13,7 +10,105 @@ tags:
 - instruct
 - it
 - abliterated
-library_name: transformers
+base_model: mistralai/Mistral-Small-Instruct-2409
+license_name: mrl
+license_link: https://mistral.ai/licenses/MRL-0.1.md
+pipeline_tag: text-generation
+model-index:
+- name: Mistral-Small-Instruct-2409-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: 69.71
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Mistral-Small-Instruct-2409-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: 31.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Mistral-Small-Instruct-2409-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: 14.12
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Mistral-Small-Instruct-2409-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: 11.07
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Mistral-Small-Instruct-2409-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: 3.55
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Mistral-Small-Instruct-2409-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: 32.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Mistral-Small-Instruct-2409-abliterated
+      name: Open LLM Leaderboard
 ---
 
 
@@ -25,3 +120,17 @@ library_name: transformers
 Check out the <a href="https://huggingface.co/byroneverson/Mistral-Small-Instruct-2409-abliterated/blob/main/abliterate-mistral-small-instruct-2409.ipynb">jupyter notebook</a> for details of how this model was abliterated.
 
 ![Logo](https://huggingface.co/byroneverson/Mistral-Small-Instruct-2409-abliterated/resolve/main/logo.png "Logo")
+
+# [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_byroneverson__Mistral-Small-Instruct-2409-abliterated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.03|
+|IFEval (0-Shot)    |69.71|
+|BBH (3-Shot)       |31.26|
+|MATH Lvl 5 (4-Shot)|14.12|
+|GPQA (0-shot)      |11.07|
+|MuSR (0-shot)      | 3.55|
+|MMLU-PRO (5-shot)  |32.48|
+