论文、相关资源和引用方式

以下学术作品按时间倒序排列。

SpQR：一种用于近乎无损 LLM 权重压缩的稀疏量化表示（2023 年 6 月）

作者：Tim Dettmers、Ruslan Svirschevski、Vage Egiazarian、Denis Kuznedelev、Elias Frantar、Saleh Ashkboos、Alexander Borzunov、Torsten Hoefler、Dan Alistarh

Twitter 摘要线程

@article{dettmers2023spqr,
  title={SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression},
  author={Dettmers, Tim and Svirschevski, Ruslan and Egiazarian, Vage and Kuznedelev, Denis and Frantar, Elias and Ashkboos, Saleh and Borzunov, Alexander and Hoefler, Torsten and Alistarh, Dan},
  journal={arXiv preprint arXiv:2306.03078},
  year={2023}
}

QLoRA：量化 LLM 的高效微调（2023 年 5 月）

作者：Tim Dettmers、Artidoro Pagnoni、Ari Holtzman、Luke Zettlemoyer

@article{dettmers2023qlora,
  title={Qlora: Efficient finetuning of quantized llms},
  author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
  journal={arXiv preprint arXiv:2305.14314},
  year={2023}
}

4 位精度的论据：k 位推理缩放定律（2022 年 12 月）

作者：Tim Dettmers、Luke Zettlemoyer

@inproceedings{dettmers2023case,
  title={The case for 4-bit precision: k-bit inference scaling laws},
  author={Dettmers, Tim and Zettlemoyer, Luke},
  booktitle={International Conference on Machine Learning},
  pages={7750--7774},
  year={2023},
  organization={PMLR}
}

LLM.int8()：面向大规模 Transformers 的 8 位矩阵乘法（2022 年 11 月）

作者：Tim Dettmers、Mike Lewis、Younes Belkada、Luke Zettlemoyer

@article{dettmers2022llm,
  title={Llm. int8 (): 8-bit matrix multiplication for transformers at scale},
  author={Dettmers, Tim and Lewis, Mike and Belkada, Younes and Zettlemoyer, Luke},
  journal={arXiv preprint arXiv:2208.07339},
  year={2022}
}

通过分块量化实现 8 位优化器（2021 年 10 月）

作者：Tim Dettmers、Mike Lewis、Sam Shleifer、Luke Zettlemoyer

@article{DBLP:journals/corr/abs-2110-02861,
  author       = {Tim Dettmers and
                  Mike Lewis and
                  Sam Shleifer and
                  Luke Zettlemoyer},
  title        = {8-bit Optimizers via Block-wise Quantization},
  journal      = {CoRR},
  volume       = {abs/2110.02861},
  year         = {2021},
  url          = {https://arxiv.org/abs/2110.02861},
  eprinttype    = {arXiv},
  eprint       = {2110.02861},
  timestamp    = {Thu, 21 Oct 2021 16:20:08 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-02861.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}