Adding Evaluation Results

README.md

@@ -1,5 +1,4 @@
 ---
-inference: false
 language:
 - ja
 - en
@@ -8,6 +7,110 @@ language:
 - zh
 - cs
 license: llama2
+inference: false
+model-index:
+- name: ALMA-7B-Ja-V2
+  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: 52.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=webbigdata/ALMA-7B-Ja-V2
+      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: 77.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=webbigdata/ALMA-7B-Ja-V2
+      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: 44.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=webbigdata/ALMA-7B-Ja-V2
+      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: 38.66
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=webbigdata/ALMA-7B-Ja-V2
+      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: 73.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=webbigdata/ALMA-7B-Ja-V2
+      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=webbigdata/ALMA-7B-Ja-V2
+      name: Open LLM Leaderboard
 ---
 # New Translation model released.
 
@@ -175,4 +278,17 @@ Prevous Model [ALMA-7B-Ja](https://huggingface.co/webbigdata/ALMA-7B-Ja). (13.3
 
 
 ## about this work
-- **This work was done by :** [webbigdata](https://webbigdata.jp/post-21151/).
+- **This work was done by :** [webbigdata](https://webbigdata.jp/post-21151/).
+# [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_webbigdata__ALMA-7B-Ja-V2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |47.85|
+|AI2 Reasoning Challenge (25-Shot)|52.39|
+|HellaSwag (10-Shot)              |77.92|
+|MMLU (5-Shot)                    |44.72|
+|TruthfulQA (0-shot)              |38.66|
+|Winogrande (5-shot)              |73.40|
+|GSM8k (5-shot)                   | 0.00|
+