metadata
license: mit
TinyLlama-NoPE-HeadScale8k
Citation
@misc{wang2024length,
title={Length Generalization of Causal Transformers without Position Encoding},
author={Jie Wang and Tao Ji and Yuanbin Wu and Hang Yan and Tao Gui and Qi Zhang and Xuanjing Huang and Xiaoling Wang},
year={2024},
eprint={2404.12224},
archivePrefix={arXiv},
primaryClass={cs.CL}
}