{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:21:04Z","timestamp":1778692864301,"version":"3.51.4"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,8]]},"DOI":"10.1109\/cis-ram61939.2024.10672819","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:36:11Z","timestamp":1726508171000},"page":"368-373","source":"Crossref","is-referenced-by-count":2,"title":["GPTQT: Quantize Large Language Models Twice to Push the Efficiency"],"prefix":"10.1109","author":[{"given":"Yipin","family":"Guo","sequence":"first","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilin","family":"Lang","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinyuan","family":"Ren","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3389497"},{"key":"ref2","article-title":"opt: open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref3","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Xiao"},{"key":"ref4","first-page":"30318","article-title":"Gpt3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Dettmers","year":"2022"},{"key":"ref5","first-page":"10088","article-title":"Qlora: Efficient finetuning of quantized llms","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dettmers","year":"2023"},{"key":"ref6","article-title":"QA-loRA: Quantization-aware low-rank adaptation of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu"},{"key":"ref7","article-title":"Awq: Activation-aware weight quantization for llm compression and acceleration","author":"Lin","year":"2023"},{"key":"ref8","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Frantar"},{"key":"ref9","article-title":"Billm: Pushing the limit of post-training quantization for llms","author":"Huang","year":"2024"},{"key":"ref10","article-title":"Post-training weighted quantization of neural networks for language models","author":"Kwon","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref12","article-title":"optimal brain compression: A framework for accurate post-training quantization and pruning","author":"Frantar","year":"2023"},{"key":"ref13","article-title":"LUT-GEMM: Quantized matrix multiplication based on LUTs for efficient inference in large-scale generative language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Park"},{"key":"ref14","first-page":"27168","article-title":"Zeroquant: Efficient and affordable post-training quantization for large-scale transformers","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Yao","year":"2022"},{"key":"ref15","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"workshop","year":"2023"},{"key":"ref16","article-title":"Llama: open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref17","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref18","article-title":"Seq2biseq: Bidirectional output-wise recurrent neural networks for sequence modelling","author":"Dinarelli","year":"2019"}],"event":{"name":"2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM)","location":"Hangzhou, China","start":{"date-parts":[[2024,8,8]]},"end":{"date-parts":[[2024,8,11]]}},"container-title":["2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10672625\/10672631\/10672819.pdf?arnumber=10672819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T06:12:18Z","timestamp":1726899138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10672819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,8]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/cis-ram61939.2024.10672819","relation":{},"subject":[],"published":{"date-parts":[[2024,8,8]]}}}