Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
 language:
 - ko
-library_name: transformers
-pipeline_tag: text-generation
 license: cc-by-nc-sa-4.0
+library_name: transformers
 tags:
 - merge
+pipeline_tag: text-generation
+model-index:
+- name: SOLARC-M-10.7B
+  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: 71.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/SOLARC-M-10.7B
+      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: 88.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/SOLARC-M-10.7B
+      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: 66.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/SOLARC-M-10.7B
+      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: 71.85
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/SOLARC-M-10.7B
+      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: 83.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/SOLARC-M-10.7B
+      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: 65.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DopeorNope/SOLARC-M-10.7B
+      name: Open LLM Leaderboard
 ---
 **The license is `cc-by-nc-sa-4.0`.**  
   
@@ -63,4 +166,17 @@ 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__SOLARC-M-10.7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.42|
+|AI2 Reasoning Challenge (25-Shot)|71.16|
+|HellaSwag (10-Shot)              |88.41|
+|MMLU (5-Shot)                    |66.31|
+|TruthfulQA (0-shot)              |71.85|
+|Winogrande (5-shot)              |83.35|
+|GSM8k (5-shot)                   |65.43|
+