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

@@ -1,12 +1,115 @@
 ---
 language:
 - en
+license: cc-by-nc-sa-4.0
 datasets:
 - Intel/orca_dpo_pairs
 - argilla/distilabel-math-preference-dpo
 - kyujinpy/orca_math_dpo
 pipeline_tag: text-generation
-license: cc-by-nc-sa-4.0
+model-index:
+- name: Sakura-SOLRCA-Math-Instruct-DPO-v1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 71.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 88.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 66.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 72.12
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 82.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v1
+      name: Open LLM Leaderboard
 ---
 
 # **Sakura-SOLRCA-Math-Instruct-DPO-v1**  
@@ -55,4 +158,17 @@ OpenOrca = AutoModelForCausalLM.from_pretrained(
 OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
 ```
 
----
+---
+# [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_kyujinpy__Sakura-SOLRCA-Math-Instruct-DPO-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.13|
+|AI2 Reasoning Challenge (25-Shot)|71.25|
+|HellaSwag (10-Shot)              |88.48|
+|MMLU (5-Shot)                    |66.21|
+|TruthfulQA (0-shot)              |72.12|
+|Winogrande (5-shot)              |82.87|
+|GSM8k (5-shot)                   |63.84|
+