Adding Evaluation Results (#4)

- Adding Evaluation Results (ea63910f22646e293602790d574efdf7f03036a0)


Co-authored-by: ก้องภพ จำเริญสุข <[email protected]>

README.md

@@ -1,12 +1,115 @@
 ---
+language:
+- th
+- en
 license: llama2
 datasets:
 - HuggingFaceH4/ultrachat_200k
 - HuggingFaceH4/ultrafeedback_binarized
 - HuggingFaceH4/cai-conversation-harmless
-language:
-- th
-- en
+model-index:
+- name: SambaLingo-Thai-Chat
+  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: 52.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
+      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: 78.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
+      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: 43.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
+      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: 40.84
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
+      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: 72.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
+      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: 8.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat
+      name: Open LLM Leaderboard
 ---
 
 
@@ -133,3 +236,17 @@ We would like to give a special thanks to the following groups:
   version = {1.0},
 }
 ```
+
+# [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_sambanovasystems__SambaLingo-Thai-Chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |49.45|
+|AI2 Reasoning Challenge (25-Shot)|52.73|
+|HellaSwag (10-Shot)              |78.42|
+|MMLU (5-Shot)                    |43.95|
+|TruthfulQA (0-shot)              |40.84|
+|Winogrande (5-shot)              |72.22|
+|GSM8k (5-shot)                   | 8.57|
+