Adding Evaluation Results

README.md

@@ -1,6 +1,101 @@
 ---
 library_name: transformers
 tags: []
+model-index:
+- name: LION-LLaMA-3-8b-sft-v1.0
+  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: 38.17
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0
+      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: 30.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0
+      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: 8.46
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0
+      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=Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0
+      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: 15.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0
+      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: 24.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for LION-LLaMA-3-8b-sft-v1.0
@@ -97,4 +192,17 @@ If you find this model useful in your work, please consider citing our paper:
 
 ## Acknowledgements
 
-We thank the Columbia-NLP group and [articulate.ai](https://www.articulateai.com/) for providing OpenAI API credits and computational resources to conduct our experiments.
+We thank the Columbia-NLP group and [articulate.ai](https://www.articulateai.com/) for providing OpenAI API credits and computational resources to conduct our experiments.
+# [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_Columbia-NLP__LION-LLaMA-3-8b-sft-v1.0)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.26|
+|IFEval (0-Shot)    |38.17|
+|BBH (3-Shot)       |30.88|
+|MATH Lvl 5 (4-Shot)| 8.46|
+|GPQA (0-shot)      | 3.69|
+|MuSR (0-shot)      |15.48|
+|MMLU-PRO (5-shot)  |24.86|
+