TITLE = 'Open Multilingual LLM Evaluation Leaderboard
'
INTRO_TEXT = f"""
## About
This leaderboard shows the performance of pretrained models in 29 languages on four benchmarks:
- AI2 Reasoning Challenge (25-shot)
- HellaSwag (10-shot)
- MMLU (5-shot)
- TruthfulQA (0-shot)
The evaluation data was translated into 29 languages using ChatGPT.
"""
HOW_TO = f"""
## How to list your model performance on this leaderboard:
Send an email with title [Open mLLM Loaderboard] to vietl@uoregon.edu with the huggingface's model name.
We will run your model on the four benchmarks and add it to the leaderboard.
"""
CITATION = f"""
## Citation
```
@misc{{lai2023openllmbenchmark,
author = {{Viet Lai and Nghia Trung Ngo and Amir Pouran Ben Veyseh and Franck Dernoncourt and Thien Huu Nguyen}},
title={{Open Multilingual LLM Evaluation Leaderboard}},
year={{2023}}
}}
```
"""