Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
-license: llama2
 language:
 - ja
 - en
-inference: false
+license: llama2
 datasets:
 - databricks/databricks-dolly-15k
 - kunishou/databricks-dolly-15k-ja
 - izumi-lab/llm-japanese-dataset
+thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
+inference: false
+model-index:
+- name: youri-7b-chat
+  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: 51.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
+      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: 76.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
+      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: 46.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
+      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: 41.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
+      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: 75.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
+      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: 1.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
+      name: Open LLM Leaderboard
 ---
 
 # `rinna/youri-7b-chat`
@@ -176,4 +279,17 @@ The model uses the original llama-2 tokenizer.
 ---
 
 # License
-[The llama2 license](https://ai.meta.com/llama/license/)
+[The llama2 license](https://ai.meta.com/llama/license/)
+# [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_rinna__youri-7b-chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |48.51|
+|AI2 Reasoning Challenge (25-Shot)|51.19|
+|HellaSwag (10-Shot)              |76.09|
+|MMLU (5-Shot)                    |46.06|
+|TruthfulQA (0-shot)              |41.17|
+|Winogrande (5-shot)              |75.06|
+|GSM8k (5-shot)                   | 1.52|
+