Adding Evaluation Results

README.md

@@ -1,8 +1,111 @@
 ---
-license: llama2
 language:
 - ja
 - en
+license: llama2
+model-index:
+- name: ELYZA-japanese-Llama-2-13b-fast-instruct
+  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: 57.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elyza/ELYZA-japanese-Llama-2-13b-fast-instruct
+      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: 81.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elyza/ELYZA-japanese-Llama-2-13b-fast-instruct
+      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: 54.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elyza/ELYZA-japanese-Llama-2-13b-fast-instruct
+      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: 43.82
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elyza/ELYZA-japanese-Llama-2-13b-fast-instruct
+      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: 75.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elyza/ELYZA-japanese-Llama-2-13b-fast-instruct
+      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: 2.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=elyza/ELYZA-japanese-Llama-2-13b-fast-instruct
+      name: Open LLM Leaderboard
 ---
 
 ## ELYZA-japanese-Llama-2-13b-fast-instruct
@@ -101,4 +204,17 @@ Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Plat
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-```
+```
+# [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_elyza__ELYZA-japanese-Llama-2-13b-fast-instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.72|
+|AI2 Reasoning Challenge (25-Shot)|57.51|
+|HellaSwag (10-Shot)              |81.82|
+|MMLU (5-Shot)                    |54.52|
+|TruthfulQA (0-shot)              |43.82|
+|Winogrande (5-shot)              |75.93|
+|GSM8k (5-shot)                   | 2.73|
+