Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,22 +1,125 @@
 ---
-license: mit
-datasets:
-- TIGER-Lab/MetricInstruct
 language:
 - en
 - zh
 - ru
 - cs
-metrics:
-- pearsonr
-- spearmanr
-pipeline_tag: text2text-generation
+license: mit
 tags:
 - text evaluation
 - metric
 - llm metric
 - llama
 - tigerscore
+datasets:
+- TIGER-Lab/MetricInstruct
+metrics:
+- pearsonr
+- spearmanr
+pipeline_tag: text2text-generation
+model-index:
+- name: TIGERScore-13B
+  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: 59.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TIGER-Lab/TIGERScore-13B
+      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: 82.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TIGER-Lab/TIGERScore-13B
+      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: 55.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TIGER-Lab/TIGERScore-13B
+      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: 40.38
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TIGER-Lab/TIGERScore-13B
+      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: 74.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TIGER-Lab/TIGERScore-13B
+      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: 28.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TIGER-Lab/TIGERScore-13B
+      name: Open LLM Leaderboard
 ---
 
 
@@ -201,4 +304,17 @@ If you find our work useful, please cite our paper:
   journal={arXiv preprint arXiv:2310.00752},
   year={2023}
 }
-```
+```
+# [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_TIGER-Lab__TIGERScore-13B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |56.79|
+|AI2 Reasoning Challenge (25-Shot)|59.04|
+|HellaSwag (10-Shot)              |82.79|
+|MMLU (5-Shot)                    |55.07|
+|TruthfulQA (0-shot)              |40.38|
+|Winogrande (5-shot)              |74.74|
+|GSM8k (5-shot)                   |28.73|
+