Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
-license: apache-2.0
 language:
 - th
 - en
+license: apache-2.0
 library_name: transformers
-pipeline_tag: text-generation
 tags:
 - openthaigpt
 - llama
+pipeline_tag: text-generation
+model-index:
+- name: openthaigpt-1.0.0-beta-13b-chat-hf
+  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: 53.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf
+      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: 79.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf
+      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: 51.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf
+      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: 44.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf
+      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: 73.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf
+      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: 0.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf
+      name: Open LLM Leaderboard
 ---
 
 # 🇹🇭 OpenThaiGPT 13b 1.0.0-beta Chat with 16 bits in Huggingface's format.
@@ -78,3 +181,17 @@ curl --request POST \
 * Pitikorn Khlaisamniang (pitikorn32@gmail.com)
 
 <i>Disclaimer: Provided responses are not guaranteed.</i>
+
+# [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_openthaigpt__openthaigpt-1.0.0-beta-13b-chat-hf)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |50.45|
+|AI2 Reasoning Challenge (25-Shot)|53.58|
+|HellaSwag (10-Shot)              |79.09|
+|MMLU (5-Shot)                    |51.13|
+|TruthfulQA (0-shot)              |44.16|
+|Winogrande (5-shot)              |73.88|
+|GSM8k (5-shot)                   | 0.83|
+