Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-license: cc-by-4.0
-datasets:
-- cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental
 language:
 - ja
 - en
-base_model: "cyberagent/calm2-7b-chat"
+license: cc-by-4.0
+datasets:
+- cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental
+base_model: cyberagent/calm2-7b-chat
+model-index:
+- name: calm2-7b-chat-dpo-experimental
+  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: 41.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
+      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: 68.99
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
+      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: 39.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
+      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: 43.13
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
+      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: 65.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
+      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: 5.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for "calm2-7b-chat-dpo-experimental"
@@ -77,4 +180,17 @@ output_ids = model.generate(
 
 ## Author
 
-Yuu Jinnai (jinnai_yu@cyberagent.co.jp), Standing on the shoulders of giants
+Yuu Jinnai (jinnai_yu@cyberagent.co.jp), Standing on the shoulders of giants
+# [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_cyberagent__calm2-7b-chat-dpo-experimental)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |44.03|
+|AI2 Reasoning Challenge (25-Shot)|41.04|
+|HellaSwag (10-Shot)              |68.99|
+|MMLU (5-Shot)                    |39.82|
+|TruthfulQA (0-shot)              |43.13|
+|Winogrande (5-shot)              |65.67|
+|GSM8k (5-shot)                   | 5.53|
+