Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Update src/assets/text_content.py
Browse files- src/assets/text_content.py +60 -0
src/assets/text_content.py
CHANGED
@@ -97,4 +97,64 @@ CITATION_BUTTON_TEXT = r"""
|
|
97 |
publisher = {Upstage, National Information Society Agency},
|
98 |
howpublished = "\url{https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard}"
|
99 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
"""
|
|
|
97 |
publisher = {Upstage, National Information Society Agency},
|
98 |
howpublished = "\url{https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard}"
|
99 |
}
|
100 |
+
@software{eval-harness,
|
101 |
+
author = {Gao, Leo and
|
102 |
+
Tow, Jonathan and
|
103 |
+
Biderman, Stella and
|
104 |
+
Black, Sid and
|
105 |
+
DiPofi, Anthony and
|
106 |
+
Foster, Charles and
|
107 |
+
Golding, Laurence and
|
108 |
+
Hsu, Jeffrey and
|
109 |
+
McDonell, Kyle and
|
110 |
+
Muennighoff, Niklas and
|
111 |
+
Phang, Jason and
|
112 |
+
Reynolds, Laria and
|
113 |
+
Tang, Eric and
|
114 |
+
Thite, Anish and
|
115 |
+
Wang, Ben and
|
116 |
+
Wang, Kevin and
|
117 |
+
Zou, Andy},
|
118 |
+
title = {A framework for few-shot language model evaluation},
|
119 |
+
month = sep,
|
120 |
+
year = 2021,
|
121 |
+
publisher = {Zenodo},
|
122 |
+
version = {v0.0.1},
|
123 |
+
doi = {10.5281/zenodo.5371628},
|
124 |
+
url = {https://doi.org/10.5281/zenodo.5371628}
|
125 |
+
}
|
126 |
+
@misc{seo2023kocommongen,
|
127 |
+
title={Korean Commonsense Reasoning Evaluation for Large Language Models},
|
128 |
+
author={Jaehyung Seo, Chanjun Park, Hyeonseok Moon, Sugyeong Eo, Aram So, Heuiseok Lim},
|
129 |
+
year={2023},
|
130 |
+
affilation={Korea University, NLP&AI},
|
131 |
+
booktitle={Proceedings of the 35th Annual Conference on Human & Cognitive Language Technology}}
|
132 |
+
@misc{park2023koarc,
|
133 |
+
title={Ko-ARC},
|
134 |
+
original_title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
|
135 |
+
author={Hyunbyung Park, Chanjun Park},
|
136 |
+
original_author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
|
137 |
+
year={2023}
|
138 |
+
}
|
139 |
+
@misc{park2023kohellaswag,
|
140 |
+
title={Ko-HellaSwag},
|
141 |
+
original_title={HellaSwag: Can a Machine Really Finish Your Sentence?},
|
142 |
+
author={Hyunbyung Park, Chanjun Park},
|
143 |
+
original_author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
|
144 |
+
year={2023}
|
145 |
+
}
|
146 |
+
@misc{park2023kommlu,
|
147 |
+
title={Ko-MMLU},
|
148 |
+
original_title={Measuring Massive Multitask Language Understanding},
|
149 |
+
author={Hyunbyung Park, Chanjun Park},
|
150 |
+
original_author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
|
151 |
+
year={2023}
|
152 |
+
}
|
153 |
+
@misc{park2023kotruthfulqa,
|
154 |
+
title={Ko-TruthfulQA},
|
155 |
+
original_title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
|
156 |
+
author={Hyunbyung Park, Chanjun Park},
|
157 |
+
original_author={Stephanie Lin and Jacob Hilton and Owain Evans},
|
158 |
+
year={2023}
|
159 |
+
}
|
160 |
"""
|