Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
-license: apache-2.0
 language:
 - ja
 - en
+license: apache-2.0
 datasets:
 - augmxnt/ultra-orca-boros-en-ja-v1
 - Open-Orca/SlimOrca
 - augmxnt/shisa-en-ja-dpo-v1
+model-index:
+- name: shisa-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: 56.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-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: 78.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-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-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: 52.49
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-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: 78.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-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: 41.62
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augmxnt/shisa-7b-v1
+      name: Open LLM Leaderboard
 ---
 # Shisa 7B
 
@@ -376,4 +479,17 @@ print(tokenizer.apply_chat_template(chat, tokenize=False))
 
 また、貴重なヒューマンプリファレンステストを提供してくださったすべてのボランティアにも感謝いたします！
 
-このプロジェクトのためにより良く、より大きなモデルを訓練するために、追加の計算を積極的に探しています。お問い合わせは次の宛先までお願いいたします：*compute at augmxnt dot com*
+このプロジェクトのためにより良く、より大きなモデルを訓練するために、追加の計算を積極的に探しています。お問い合わせは次の宛先までお願いいたします：*compute at augmxnt dot com*
+# [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-7b-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |55.01|
+|AI2 Reasoning Challenge (25-Shot)|56.14|
+|HellaSwag (10-Shot)              |78.63|
+|MMLU (5-Shot)                    |23.12|
+|TruthfulQA (0-shot)              |52.49|
+|Winogrande (5-shot)              |78.06|
+|GSM8k (5-shot)                   |41.62|
+