Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,17 +1,19 @@
 ---
-base_model:
-- SanjiWatsuki/Silicon-Maid-7B
-- Guilherme34/Samantha-v2
-- jan-hq/stealth-v1.3
-- mitultiwari/mistral-7B-instruct-dpo
-- senseable/WestLake-7B-v2
+language:
+- en
+license: cc
 library_name: transformers
 tags:
 - mergekit
 - merge
 datasets:
 - Anthropic/hh-rlhf
-license: cc
+base_model:
+- SanjiWatsuki/Silicon-Maid-7B
+- Guilherme34/Samantha-v2
+- jan-hq/stealth-v1.3
+- mitultiwari/mistral-7B-instruct-dpo
+- senseable/WestLake-7B-v2
 model-index:
 - name: sethuiyer/Aika-7B
   results:
@@ -30,8 +32,7 @@ model-index:
       value: 65.36
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -47,8 +48,7 @@ model-index:
       value: 81.49
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -65,8 +65,7 @@ model-index:
       value: 53.91
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -82,8 +81,7 @@ model-index:
     - type: mc2
       value: 51.22
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -100,8 +98,7 @@ model-index:
       value: 77.74
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -118,11 +115,8 @@ model-index:
       value: 25.78
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
       name: Open LLM Leaderboard
-language:
-- en
 ---
 # Aika-7B
 
@@ -158,4 +152,17 @@ You get Aika - a considerate, personal digital assistant.
 
 ### Configuration
 
-Please check [mergekit_config.yml](https://huggingface.co/sethuiyer/Aika-7B/blob/main/mergekit_config.yml) for the merge config.
+Please check [mergekit_config.yml](https://huggingface.co/sethuiyer/Aika-7B/blob/main/mergekit_config.yml) for the merge config.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sethuiyer__Aika-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.25|
+|AI2 Reasoning Challenge (25-Shot)|65.36|
+|HellaSwag (10-Shot)              |81.49|
+|MMLU (5-Shot)                    |53.91|
+|TruthfulQA (0-shot)              |51.22|
+|Winogrande (5-shot)              |77.74|
+|GSM8k (5-shot)                   |25.78|
+