Adding Evaluation Results (#1)

- Adding Evaluation Results (4c6b678c2d87ebaab6bd290f6efa30cd356674dd)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,16 +1,111 @@
 ---
-license: llama3
-datasets:
-- jed351/cantonese-wikipedia
-- lordjia/Cantonese_English_Translation
 language:
 - en
 - zh
-pipeline_tag: text-generation
+license: llama3
 tags:
 - Cantonese
 - chat
 - Llama3
+datasets:
+- jed351/cantonese-wikipedia
+- lordjia/Cantonese_English_Translation
+pipeline_tag: text-generation
+model-index:
+- name: Llama-3-Cantonese-8B-Instruct
+  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: 66.69
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lordjia/Llama-3-Cantonese-8B-Instruct
+      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: 26.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lordjia/Llama-3-Cantonese-8B-Instruct
+      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: 8.23
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lordjia/Llama-3-Cantonese-8B-Instruct
+      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: 5.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lordjia/Llama-3-Cantonese-8B-Instruct
+      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: 9.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lordjia/Llama-3-Cantonese-8B-Instruct
+      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: 27.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lordjia/Llama-3-Cantonese-8B-Instruct
+      name: Open LLM Leaderboard
 ---
 
 # Llama-3-Cantonese-8B-Instruct
@@ -55,4 +150,17 @@ This model is licensed under the Llama 3 Community License. Please review the te
 
 ## Contributors / 貢獻
 
-- LordJia [https://ai.chao.cool](https://ai.chao.cool/)
+- LordJia [https://ai.chao.cool](https://ai.chao.cool/)
+# [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_lordjia__Llama-3-Cantonese-8B-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.16|
+|IFEval (0-Shot)    |66.69|
+|BBH (3-Shot)       |26.79|
+|MATH Lvl 5 (4-Shot)| 8.23|
+|GPQA (0-shot)      | 5.82|
+|MuSR (0-shot)      | 9.48|
+|MMLU-PRO (5-shot)  |27.94|
+