Fetching the paper…
Reading the bibliography…
We reveal that low-bit quantization favors undertrained large language models (LLMs) by observing that models with larger sizes or fewer training tokens experience less quantization-induced degradation (QiD) when applying low-bit quantization, whereas smaller models with extensive training tokens suffer significant QiD.
Pointer sentinel mixture models
Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher · 2016
Earlier work this paper cites.
Opening the black box of deep neural networks via information
Ravid Shwartz-Ziv and Naftali Tishby · 2017
Earlier work this paper cites.
Quantization and training of neural networks for efficient integer-arithmetic-only inference
Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, and Dmitry Kalenichenko · 2018
Earlier work this paper cites.
Quantizing deep convolutional networks for efficient inference: A whitepaper
Raghuraman Krishnamoorthi · 2018
Earlier work this paper cites.
Post training 4-bit quantization of convolutional networks for rapid-deployment
Ron Banner, Yury Nahshan, and Daniel Soudry · 2019
Earlier work this paper cites.
Q8bert: Quantized 8bit bert
Ofir Zafrir, Guy Boudoukh, Peter Izsak, and Moshe Wasserblat · 2019
Earlier work this paper cites.
Binarybert: Pushing the limit of bert quantization
Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jing Jin, Xin Jiang, Qun Liu, Michael Lyu, and Irwin King · 2020
Earlier work this paper cites.
Scaling laws for neural language models
Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei · 2020
Earlier work this paper cites.
Ternarybert: Distillation-aware ultra-low bit bert
Wei Zhang, Lu Hou, Yichun Yin, Lifeng Shang, Xiao Chen, Xin Jiang, and Qun Liu · 2020
Earlier work this paper cites.
Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale
Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer · 2022
Earlier work this paper cites.
Gptq: Accurate post-training quantization for generative pre-trained transformers
Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh · 2022
Earlier work this paper cites.
Training compute-optimal large language models
Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al · 2022
Cited alongside, same era.
Pythia: A suite for analyzing large language models across training and scaling
Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O’Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al · 2023
Cited alongside, same era.
Qllm: Accurate and efficient low-bitwidth quantization for large language models
Jing Liu, Ruihao Gong, Xiuying Wei, Zhiwei Dong, Jianfei Cai, and Bohan Zhuang · 2023
Cited alongside, same era.
Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay · 2023
Cited alongside, same era.
Billm: Pushing the limit of post-training quantization for llms
Wei Huang, Yangdong Liu, Haotong Qin, Ying Li, Shiming Zhang, Xianglong Liu, Michele Magno, and Xiaojuan Qi · 2024
Closest in time.
Spectra: Surprising effectiveness of pretraining ternary language models at scale
Ayush Kaushal, Tejas Vaidhya, Arnab Kumar Mondal, Tejas Pandey, Aaryan Bhagat, and Irina Rish · 2024
Closest in time.
Tanishq Kumar, Zachary Ankner, Benjamin F Spector, Blake Bordelon, Niklas Muennighoff, Mansheej Paul, Cengiz Pehlevan, Christopher Ré, and Aditi Raghunathan · 2024
Closest in time.
Awq: Activation-aware weight quantization for on-device llm compression and acceleration
Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han · 2024
Closest in time.
Kivi: A tuning-free asymmetric 2bit quantization for kv cache
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Llama 2: Open foundation and fine-tuned chat models
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al · 2023
Cited alongside, same era.
Bitnet: Scaling 1-bit transformers for large language models
Hongyu Wang, Shuming Ma, Li Dong, Shaohan Huang, Huaijie Wang, Lingxiao Ma, Fan Yang, Ruiping Wang, Yi Wu, and Furu Wei · 2023
Cited alongside, same era.
Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al · 2024
Cited alongside, same era.
Extreme compression of large language models via additive quantization
Vage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, and Dan Alistarh · 2024
Cited alongside, same era.
How numerical precision affects mathematical reasoning capabilities of llms
Guhao Feng, Kai Yang, Yuntian Gu, Xinyue Ai, Shengjie Luo, Jiacheng Sun, Di He, Zhenguo Li, and Liwei Wang · 2024
Cited alongside, same era.
Scaling synthetic data creation with 1,000,000,000 personas
Tao Ge, Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, and Dong Yu · 2024
Cited alongside, same era.
Zirui Liu, Jiayi Yuan, Hongye Jin, Shaochen Zhong, Zhaozhuo Xu, Vladimir Braverman, Beidi Chen, and Xia Hu · 2024
Closest in time.
The era of 1-bit llms: All large language models are in 1.58 bits
Shuming Ma, Hongyu Wang, Lingxiao Ma, Lei Wang, Wenhui Wang, Shaohan Huang, Li Dong, Ruiping Wang, Jilong Xue, and Furu Wei · 2024
Closest in time.
Agile-quant: Activation-guided quantization for faster inference of llms on the edge
Xuan Shen, Peiyan Dong, Lei Lu, Zhenglun Kong, Zhengang Li, Ming Lin, Chao Wu, and Yanzhi Wang · 2024
Closest in time.
An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al · 2024
Closest in time.
Lqer: Low-rank quantization error reconstruction for llms
Cheng Zhang, Jianyi Cheng, George A Constantinides, and Yiren Zhao · 2024
Closest in time.
Erq: Error reduction for post-training quantization of vision transformers
Yunshan Zhong, Jiawei Hu, You Huang, Yuxin Zhang, and Rongrong Ji · 2024
Closest in time.