Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-license: apache-2.0
 language:
 - en
 - ja
+license: apache-2.0
 datasets:
 - augmxnt/shisa-pretrain-en-ja-v1
 - allenai/MADLAD-400
+model-index:
+- name: shisa-base-7b-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: 52.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-base-7b-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: 77.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-base-7b-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: 23.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-base-7b-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: 42.4
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-base-7b-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: 78.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-base-7b-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: 35.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-base-7b-v1
+      name: Open LLM Leaderboard
 ---
 # shisa-base-7b-v1
 
@@ -158,4 +261,17 @@ Mistralのトークン化器を12万トークンまで拡張し、日本語の
 
 [ELYZA](https://huggingface.co/elyza)チームが公開した[トークン化器拡張アプローチ](https://zenn.dev/elyza/articles/2fd451c944649d)の詳細に感謝します。これは私たちのトークン化器の出発点として使用されました。
 
-もちろん、[Mistral AI](https://huggingface.co/mistralai)による強力なベースモデルのリリースに感謝します！
+もちろん、[Mistral AI](https://huggingface.co/mistralai)による強力なベースモデルのリリースに感謝します！
+# [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_augmxnt__shisa-base-7b-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |51.64|
+|AI2 Reasoning Challenge (25-Shot)|52.30|
+|HellaSwag (10-Shot)              |77.63|
+|MMLU (5-Shot)                    |23.12|
+|TruthfulQA (0-shot)              |42.40|
+|Winogrande (5-shot)              |78.53|
+|GSM8k (5-shot)                   |35.86|
+