pminervini's picture
update
dc1ba50
raw
history blame
No virus
1.89 kB
from src.display.utils import ModelType
TITLE = """<h1 align="center" id="space-title">πŸ€— Open Hallucinations Leaderboard</h1>"""
INTRODUCTION_TEXT = """
πŸ“ The πŸ€— Open Hallucinations Leaderboard aims to track, rank and evaluate hallucinations in LLMs and chatbots.
πŸ€— Submit a model for automated evaluation on the πŸ€— GPU cluster on the "Submit" page!
The leaderboard's backend runs the great [Eleuther AI Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) - read more details in the "About" page!
"""
LLM_BENCHMARKS_TEXT = f"""
XXX
"""
EVALUATION_QUEUE_TEXT = """
XXX
"""
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
@misc{hallucinations-leaderboard,
author = {Pasquale Minervini},
title = {Hallucinations Leaderboard},
year = {2023},
publisher = {Hugging Face},
howpublished = "\url{https://huggingface.co/spaces/hallucinations-leaderboard/leaderboard}"
}
@software{eval-harness,
author = {Gao, Leo and
Tow, Jonathan and
Biderman, Stella and
Black, Sid and
DiPofi, Anthony and
Foster, Charles and
Golding, Laurence and
Hsu, Jeffrey and
McDonell, Kyle and
Muennighoff, Niklas and
Phang, Jason and
Reynolds, Laria and
Tang, Eric and
Thite, Anish and
Wang, Ben and
Wang, Kevin and
Zou, Andy},
title = {A framework for few-shot language model evaluation},
month = sep,
year = 2021,
publisher = {Zenodo},
version = {v0.0.1},
doi = {10.5281/zenodo.5371628},
url = {https://doi.org/10.5281/zenodo.5371628}
}
}"""