StableMask: Refining Causal Masking in Decoder-only Transformer.
Qingyu Yin, Xuzheng He, Xiang Zhuang, Yu Zhao, Jianhua Yao, Xiaoyu Shen, Qiang Zhang
Browse the full ICML paper archive.
Qingyu Yin, Xuzheng He, Xiang Zhuang, Yu Zhao, Jianhua Yao, Xiaoyu Shen, Qiang Zhang
Browse the full ICML paper archive.