Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-license: apache-2.0
 language:
 - ko
+license: apache-2.0
 library_name: transformers
-pipeline_tag: text-generation
 datasets:
 - maywell/ko_Ultrafeedback_binarized
+pipeline_tag: text-generation
+model-index:
+- name: Open_Ko_SOLAR_DPO_Merge_v0.1
+  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: 55.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1
+      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: 78.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1
+      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: 54.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1
+      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: 40.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1
+      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: 75.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1
+      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: 29.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1
+      name: Open LLM Leaderboard
 ---
 
 **Explanation**
@@ -42,4 +145,17 @@ datasets:
       publisher    = { Hugging Face }
   }
   
-  ```
+  ```
+# [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_dddsaty__Open_Ko_SOLAR_DPO_Merge_v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |55.41|
+|AI2 Reasoning Challenge (25-Shot)|55.12|
+|HellaSwag (10-Shot)              |78.18|
+|MMLU (5-Shot)                    |54.19|
+|TruthfulQA (0-shot)              |40.17|
+|Winogrande (5-shot)              |75.69|
+|GSM8k (5-shot)                   |29.11|
+