Commit
•
0bd224d
1
Parent(s):
a6b218f
Update README.md
Browse files
README.md
CHANGED
@@ -65,4 +65,100 @@ pipeline = transformers.pipeline(
|
|
65 |
|
66 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
67 |
print(outputs[0]["generated_text"])
|
68 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
|
66 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
67 |
print(outputs[0]["generated_text"])
|
68 |
+
```
|
69 |
+
|
70 |
+
|
71 |
+
|
72 |
+
|
73 |
+
@misc{open-llm-leaderboard,
|
74 |
+
author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
|
75 |
+
title = {Open LLM Leaderboard},
|
76 |
+
year = {2023},
|
77 |
+
publisher = {Hugging Face},
|
78 |
+
howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
|
79 |
+
}
|
80 |
+
@software{eval-harness,
|
81 |
+
author = {Gao, Leo and
|
82 |
+
Tow, Jonathan and
|
83 |
+
Biderman, Stella and
|
84 |
+
Black, Sid and
|
85 |
+
DiPofi, Anthony and
|
86 |
+
Foster, Charles and
|
87 |
+
Golding, Laurence and
|
88 |
+
Hsu, Jeffrey and
|
89 |
+
McDonell, Kyle and
|
90 |
+
Muennighoff, Niklas and
|
91 |
+
Phang, Jason and
|
92 |
+
Reynolds, Laria and
|
93 |
+
Tang, Eric and
|
94 |
+
Thite, Anish and
|
95 |
+
Wang, Ben and
|
96 |
+
Wang, Kevin and
|
97 |
+
Zou, Andy},
|
98 |
+
title = {A framework for few-shot language model evaluation},
|
99 |
+
month = sep,
|
100 |
+
year = 2021,
|
101 |
+
publisher = {Zenodo},
|
102 |
+
version = {v0.0.1},
|
103 |
+
doi = {10.5281/zenodo.5371628},
|
104 |
+
url = {https://doi.org/10.5281/zenodo.5371628}
|
105 |
+
}
|
106 |
+
@misc{clark2018think,
|
107 |
+
title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
|
108 |
+
author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
|
109 |
+
year={2018},
|
110 |
+
eprint={1803.05457},
|
111 |
+
archivePrefix={arXiv},
|
112 |
+
primaryClass={cs.AI}
|
113 |
+
}
|
114 |
+
@misc{zellers2019hellaswag,
|
115 |
+
title={HellaSwag: Can a Machine Really Finish Your Sentence?},
|
116 |
+
author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
|
117 |
+
year={2019},
|
118 |
+
eprint={1905.07830},
|
119 |
+
archivePrefix={arXiv},
|
120 |
+
primaryClass={cs.CL}
|
121 |
+
}
|
122 |
+
@misc{hendrycks2021measuring,
|
123 |
+
title={Measuring Massive Multitask Language Understanding},
|
124 |
+
author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
|
125 |
+
year={2021},
|
126 |
+
eprint={2009.03300},
|
127 |
+
archivePrefix={arXiv},
|
128 |
+
primaryClass={cs.CY}
|
129 |
+
}
|
130 |
+
@misc{lin2022truthfulqa,
|
131 |
+
title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
|
132 |
+
author={Stephanie Lin and Jacob Hilton and Owain Evans},
|
133 |
+
year={2022},
|
134 |
+
eprint={2109.07958},
|
135 |
+
archivePrefix={arXiv},
|
136 |
+
primaryClass={cs.CL}
|
137 |
+
}
|
138 |
+
@misc{DBLP:journals/corr/abs-1907-10641,
|
139 |
+
title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale},
|
140 |
+
author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
|
141 |
+
year={2019},
|
142 |
+
eprint={1907.10641},
|
143 |
+
archivePrefix={arXiv},
|
144 |
+
primaryClass={cs.CL}
|
145 |
+
}
|
146 |
+
@misc{DBLP:journals/corr/abs-2110-14168,
|
147 |
+
title={Training Verifiers to Solve Math Word Problems},
|
148 |
+
author={Karl Cobbe and
|
149 |
+
Vineet Kosaraju and
|
150 |
+
Mohammad Bavarian and
|
151 |
+
Mark Chen and
|
152 |
+
Heewoo Jun and
|
153 |
+
Lukasz Kaiser and
|
154 |
+
Matthias Plappert and
|
155 |
+
Jerry Tworek and
|
156 |
+
Jacob Hilton and
|
157 |
+
Reiichiro Nakano and
|
158 |
+
Christopher Hesse and
|
159 |
+
John Schulman},
|
160 |
+
year={2021},
|
161 |
+
eprint={2110.14168},
|
162 |
+
archivePrefix={arXiv},
|
163 |
+
primaryClass={cs.CL}
|
164 |
+
}
|