Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: apache-2.0
+model-index:
+- name: SOLAR_KO_1.3_deup
+  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: 55.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/SOLAR_KO_1.3_deup
+      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: 79.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/SOLAR_KO_1.3_deup
+      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: 55.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/SOLAR_KO_1.3_deup
+      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: 47.55
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/SOLAR_KO_1.3_deup
+      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: 76.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/SOLAR_KO_1.3_deup
+      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: 22.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/SOLAR_KO_1.3_deup
+      name: Open LLM Leaderboard
 ---
 ## Model
 base_model : beomi/OPEN-SOLAR-KO-10.7B
@@ -24,4 +127,17 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 (24.01.29 기준 리더보드 11등)
 | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
 | ------: | -----: | -----------: | ------: | ------------: | --------------: |
-|   53.63 |  52.65 |        60.92 |   50.9  |         45.14 |           58.56 |
+|   53.63 |  52.65 |        60.92 |   50.9  |         45.14 |           58.56 |
+# [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_jingyeom__SOLAR_KO_1.3_deup)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |56.47|
+|AI2 Reasoning Challenge (25-Shot)|55.97|
+|HellaSwag (10-Shot)              |79.97|
+|MMLU (5-Shot)                    |55.88|
+|TruthfulQA (0-shot)              |47.55|
+|Winogrande (5-shot)              |76.87|
+|GSM8k (5-shot)                   |22.59|
+