Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
 language:
 - ko
+license: cc-by-nc-sa-4.0
 library_name: transformers
 pipeline_tag: text-generation
-license: cc-by-nc-sa-4.0
+model-index:
+- name: You_can_cry_Snowman-13B
+  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: 69.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/You_can_cry_Snowman-13B
+      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: 86.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/You_can_cry_Snowman-13B
+      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: 63.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/You_can_cry_Snowman-13B
+      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: 70.24
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/You_can_cry_Snowman-13B
+      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: 80.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/You_can_cry_Snowman-13B
+      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: 47.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/You_can_cry_Snowman-13B
+      name: Open LLM Leaderboard
 ---
 **The license is `cc-by-nc-sa-4.0`.**  
   
@@ -62,4 +165,17 @@ 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_DopeorNope__You_can_cry_Snowman-13B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.46|
+|AI2 Reasoning Challenge (25-Shot)|69.11|
+|HellaSwag (10-Shot)              |86.30|
+|MMLU (5-Shot)                    |63.77|
+|TruthfulQA (0-shot)              |70.24|
+|Winogrande (5-shot)              |80.27|
+|GSM8k (5-shot)                   |47.08|
+