Adding Evaluation Results

README.md

@@ -1,25 +1,128 @@
 ---
-license: apache-2.0
 language:
-  - en
-  - ja
-programming_language:
-  - C
-  - C++
-  - C#
-  - Go
-  - Java
-  - JavaScript
-  - Lua
-  - PHP
-  - Python
-  - Ruby
-  - Rust
-  - Scala
-  - TypeScript
+- en
+- ja
+license: apache-2.0
 library_name: transformers
+programming_language:
+- C
+- C++
+- C#
+- Go
+- Java
+- JavaScript
+- Lua
+- PHP
+- Python
+- Ruby
+- Rust
+- Scala
+- TypeScript
 pipeline_tag: text-generation
 inference: false
+model-index:
+- name: llm-jp-13b-instruct-full-jaster-v1.0
+  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: 27.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
+      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: 44.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
+      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=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
+      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: 44.69
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
+      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: 50.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
+      name: Open LLM Leaderboard
 ---
 # llm-jp-13b-instruct-full-jaster-v1.0
 
@@ -154,3 +257,17 @@ llm-jp(at)nii.ac.jp
 *The names are listed in alphabetical order.*
 
 Hirokazu Kiyomaru, Hiroshi Matsuda, Jun Suzuki, Namgi Han, Saku Sugawara, Shota Sasaki, Shuhei Kurita, Taishi Nakamura, Takumi Okamoto.
+
+# [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_llm-jp__llm-jp-13b-instruct-full-jaster-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |31.63|
+|AI2 Reasoning Challenge (25-Shot)|27.22|
+|HellaSwag (10-Shot)              |44.70|
+|MMLU (5-Shot)                    |23.12|
+|TruthfulQA (0-shot)              |44.69|
+|Winogrande (5-shot)              |50.04|
+|GSM8k (5-shot)                   | 0.00|
+