Adding Evaluation Results

README.md

@@ -1,5 +1,12 @@
 ---
+language:
+- th
+- en
 license: apache-2.0
+library_name: transformers
+tags:
+- openthaigpt
+- llama
 datasets:
 - kobkrit/rd-taxqa
 - iapp_wiki_qa_squad
@@ -10,14 +17,110 @@ datasets:
 - Thaweewat/gpteacher-20k-th
 - Thaweewat/onet-m6-social
 - Thaweewat/alpaca-finance-43k-th
-language:
-- th
-- en
-library_name: transformers
 pipeline_tag: text-generation
-tags:
-- openthaigpt
-- llama
+model-index:
+- name: openthaigpt-1.0.0-beta-7b-chat-ckpt-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: 44.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-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: 70.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-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: 36.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-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: 49.99
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-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: 69.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-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: 1.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
+      name: Open LLM Leaderboard
 ---
 
 # 🇹🇭 OpenThaiGPT 1.0.0-beta
@@ -74,4 +177,17 @@ OpenThaiGPT Volunteers, Artificial Intelligence Entrepreneur Association of Thai
 * Kriangkrai Saetan (kraitan.ss21@gmail.com)
 * Pitikorn Khlaisamniang (pitikorn32@gmail.com)
 
-<i>Disclaimer: Provided responses are not guaranteed.</i>
+<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-7b-chat-ckpt-hf)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |45.35|
+|AI2 Reasoning Challenge (25-Shot)|44.97|
+|HellaSwag (10-Shot)              |70.19|
+|MMLU (5-Shot)                    |36.22|
+|TruthfulQA (0-shot)              |49.99|
+|Winogrande (5-shot)              |69.38|
+|GSM8k (5-shot)                   | 1.36|
+