Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
adding citations
Browse files- content.py +58 -0
content.py
CHANGED
@@ -68,5 +68,63 @@ CITATION_BUTTON_TEXT = r"""@misc{open-llm-leaderboard,
|
|
68 |
publisher = {Hugging Face},
|
69 |
howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
|
70 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
}"""
|
72 |
|
|
|
68 |
publisher = {Hugging Face},
|
69 |
howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
|
70 |
|
71 |
+
}
|
72 |
+
@software{eval-harness,
|
73 |
+
author = {Gao, Leo and
|
74 |
+
Tow, Jonathan and
|
75 |
+
Biderman, Stella and
|
76 |
+
Black, Sid and
|
77 |
+
DiPofi, Anthony and
|
78 |
+
Foster, Charles and
|
79 |
+
Golding, Laurence and
|
80 |
+
Hsu, Jeffrey and
|
81 |
+
McDonell, Kyle and
|
82 |
+
Muennighoff, Niklas and
|
83 |
+
Phang, Jason and
|
84 |
+
Reynolds, Laria and
|
85 |
+
Tang, Eric and
|
86 |
+
Thite, Anish and
|
87 |
+
Wang, Ben and
|
88 |
+
Wang, Kevin and
|
89 |
+
Zou, Andy},
|
90 |
+
title = {A framework for few-shot language model evaluation},
|
91 |
+
month = sep,
|
92 |
+
year = 2021,
|
93 |
+
publisher = {Zenodo},
|
94 |
+
version = {v0.0.1},
|
95 |
+
doi = {10.5281/zenodo.5371628},
|
96 |
+
url = {https://doi.org/10.5281/zenodo.5371628}
|
97 |
+
}
|
98 |
+
@misc{clark2018think,
|
99 |
+
title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
|
100 |
+
author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
|
101 |
+
year={2018},
|
102 |
+
eprint={1803.05457},
|
103 |
+
archivePrefix={arXiv},
|
104 |
+
primaryClass={cs.AI}
|
105 |
+
}
|
106 |
+
@misc{zellers2019hellaswag,
|
107 |
+
title={HellaSwag: Can a Machine Really Finish Your Sentence?},
|
108 |
+
author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
|
109 |
+
year={2019},
|
110 |
+
eprint={1905.07830},
|
111 |
+
archivePrefix={arXiv},
|
112 |
+
primaryClass={cs.CL}
|
113 |
+
}
|
114 |
+
@misc{hendrycks2021measuring,
|
115 |
+
title={Measuring Massive Multitask Language Understanding},
|
116 |
+
author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
|
117 |
+
year={2021},
|
118 |
+
eprint={2009.03300},
|
119 |
+
archivePrefix={arXiv},
|
120 |
+
primaryClass={cs.CY}
|
121 |
+
}
|
122 |
+
@misc{lin2022truthfulqa,
|
123 |
+
title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
|
124 |
+
author={Stephanie Lin and Jacob Hilton and Owain Evans},
|
125 |
+
year={2022},
|
126 |
+
eprint={2109.07958},
|
127 |
+
archivePrefix={arXiv},
|
128 |
+
primaryClass={cs.CL}
|
129 |
}"""
|
130 |
|