3 code implementations • 28 Sep 2023 • Junjie Yin, Jiahao Dong, Yingheng Wang, Christopher De Sa, Volodymyr Kuleshov
We propose a memory-efficient finetuning algorithm for large language models (LLMs) that supports finetuning LLMs with 65B parameters in 2/3/4-bit precision on as little as one 24GB GPU.
no code implementations • 23 Feb 2023 • Jingxia Jiang, Jinbin Bai, Yun Liu, Junjie Yin, Sixiang Chen, Tian Ye, ErKang Chen
Underwater images typically experience mixed degradations of brightness and structure caused by the absorption and scattering of light by suspended particles.
no code implementations • ICCV 2023 • Tian Ye, Sixiang Chen, Jinbin Bai, Jun Shi, Chenghao Xue, Jingxia Jiang, Junjie Yin, ErKang Chen, Yun Liu
Inspired by recent advancements in codebook and vector quantization (VQ) techniques, we present a novel Adverse Weather Removal network with Codebook Priors (AWRCP) to address the problem of unified adverse weather removal.
no code implementations • 4 Feb 2021 • Junjie Yin
In the integrated energy system (IES), the current research about the power-to-gas (P2G) technology mainly focuses on the injection of hydrogen generated from renewable energy electrolyzed water into natural gas pipelines, which may cause hydrogen embrittlement of the pipeline and cannot be repaired.
no code implementations • 9 Oct 2019 • Junjie Yin, Zixun Chen, Kelai Zhou, Chongyuan Yu
In this paper, we propose Evebot, an innovative, sequence to sequence (Seq2seq) based, fully generative conversational system for the diagnosis of negative emotions and prevention of depression through positively suggestive responses.