Adding Evaluation Results

README.md

@@ -1,10 +1,9 @@
 ---
-base_model: 01-ai/Yi-1.5-9B-Chat-16K
-license: apache-2.0
-pipeline_tag: text-generation
 language:
 - zh
 - en
+license: apache-2.0
+library_name: transformers
 tags:
 - llm
 - long context
@@ -12,7 +11,103 @@ tags:
 - chat
 - it
 - abliterated
-library_name: transformers
+base_model: 01-ai/Yi-1.5-9B-Chat-16K
+pipeline_tag: text-generation
+model-index:
+- name: Yi-1.5-9B-Chat-16K-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: 55.28
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-16K-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: 32.84
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-16K-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: 10.65
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-16K-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: 8.39
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-16K-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: 19.68
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-16K-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: 31.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-16K-abliterated
+      name: Open LLM Leaderboard
 ---
 
 
@@ -21,4 +116,17 @@ library_name: transformers
 
 Check out the <a href="https://huggingface.co/byroneverson/Yi-1.5-9B-Chat-16K-abliterated/blob/main/abliterate-yi-1-5-9b-chat.ipynb">jupyter notebook</a> for details of how this model was abliterated from Yi-1.5-9B-Chat-16K.
 
-![Logo](https://huggingface.co/byroneverson/Yi-1.5-9B-Chat-16K-abliterated/resolve/main/logo.png "Logo")
+![Logo](https://huggingface.co/byroneverson/Yi-1.5-9B-Chat-16K-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__Yi-1.5-9B-Chat-16K-abliterated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.37|
+|IFEval (0-Shot)    |55.28|
+|BBH (3-Shot)       |32.84|
+|MATH Lvl 5 (4-Shot)|10.65|
+|GPQA (0-shot)      | 8.39|
+|MuSR (0-shot)      |19.68|
+|MMLU-PRO (5-shot)  |31.37|
+