Adding Evaluation Results

README.md

@@ -1,7 +1,102 @@
 ---
-license: apache-2.0
 language:
 - yue
+license: apache-2.0
+model-index:
+- name: CantoneseLLMChat-v0.5
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 32.31
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLMChat-v0.5
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 20.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLMChat-v0.5
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 2.79
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLMChat-v0.5
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.69
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLMChat-v0.5
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 18.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLMChat-v0.5
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 16.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLMChat-v0.5
+      name: Open LLM Leaderboard
 ---
 
 Continual pretraining model of the [Yi-6B](https://huggingface.co/01-ai/Yi-1.5-6B) model on a Cantonese corpus, which consisted of translated Hong Kong news, Wikipedia articles, subtitles, and open-sourced dialogue corpora. Additionally, we extended the vocabulary to include common Cantonese words.
@@ -109,4 +204,17 @@ The model is intended to use for Cantonese language understanding and generation
 
 ### Hallucination
 
-Most LLM also have hallucination issue, this model is no exception, it may generate incorrect or misleading information, please use it with caution.
+Most LLM also have hallucination issue, this model is no exception, it may generate incorrect or misleading information, please use it with caution.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_hon9kon9ize__CantoneseLLMChat-v0.5)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |15.73|
+|IFEval (0-Shot)    |32.31|
+|BBH (3-Shot)       |20.76|
+|MATH Lvl 5 (4-Shot)| 2.79|
+|GPQA (0-shot)      | 3.69|
+|MuSR (0-shot)      |18.13|
+|MMLU-PRO (5-shot)  |16.71|
+