{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T04:37:26Z","timestamp":1793162246066,"version":"4.5.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12202412"],"award-info":[{"award-number":["12202412"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12202413"],"award-info":[{"award-number":["12202413"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1016\/j.neunet.2025.107855","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T15:35:40Z","timestamp":1752593740000},"page":"107855","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":9,"special_numbering":"C","title":["PT-BitNet: Scaling up the 1-Bit large language model with post-training quantization"],"prefix":"10.1016","volume":"191","author":[{"given":"Yufei","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9074-2857","authenticated-orcid":false,"given":"Zecheng","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahang","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaode","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8579-4943","authenticated-orcid":false,"given":"Yuhan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanpei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9579-7686","authenticated-orcid":false,"given":"Weihang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107855_bib0001","series-title":"Large scale kernel machines","article-title":"Scaling learning algorithms towards AI","author":"Bengio","year":"2007"},{"key":"10.1016\/j.neunet.2025.107855_bib0002","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7432","article-title":"PIQA: Reasoning about physical commonsense in natural language","volume":"vol. 34","author":"Bisk","year":"2020"},{"key":"10.1016\/j.neunet.2025.107855_bib0003","unstructured":"Brown, T. B. (2020). Language models are few-shot learners. arXiv preprint arXiv:2005.14165."},{"key":"10.1016\/j.neunet.2025.107855_bib0004","unstructured":"Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S. et al. (2023). Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712."},{"key":"10.1016\/j.neunet.2025.107855_bib0005","doi-asserted-by":"crossref","unstructured":"Chou, Y., Yao, M., Wang, K., Pan, Y., Zhu, R., Zhong, Y., Qiao, Y., Wu, J., Xu, B., & Li, G. (2024). MetaLA: Unified optimal linear approximation to softmax attention map. arXiv preprint arXiv:2411.10741.","DOI":"10.52202\/079017-2270"},{"key":"10.1016\/j.neunet.2025.107855_bib0006","unstructured":"Clark, C., Lee, K., Chang, M.-W., Kwiatkowski, T., Collins, M., & Toutanova, K. (2019). BoolQ: Exploring the surprising difficulty of natural yes\/no questions. arXiv preprint arXiv:1905.10044."},{"key":"10.1016\/j.neunet.2025.107855_bib0007","unstructured":"Clark, P., Cowhey, I., Etzioni, O., Khot, T., Sabharwal, A., Schoenick, C., & Tafjord, O. (2018). Think you have solved question answering? Try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457."},{"key":"10.1016\/j.neunet.2025.107855_bib0008","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., & Zettlemoyer, L. (2022). LLM.int8( ): 8-bit matrix multiplication for transformers at scale. arXiv preprint arXiv:2208.07339."},{"key":"10.1016\/j.neunet.2025.107855_bib0009","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805."},{"key":"10.1016\/j.neunet.2025.107855_bib0010","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., & Alistarh, D. (2022). GPTQ: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323."},{"key":"10.1016\/j.neunet.2025.107855_bib0011","series-title":"Low-power computer vision","first-page":"291","article-title":"A survey of quantization methods for efficient neural network inference","author":"Gholami","year":"2022"},{"key":"10.1016\/j.neunet.2025.107855_bib0012","unstructured":"Gong, R., Yong, Y., Gu, S., Huang, Y., Zhang, Y., Liu, X., & Tao, D. (2024). LLM-QBench: A benchmark towards the best practice for post-training quantization of large language models. arXiv preprint arXiv:2405.06001."},{"key":"10.1016\/j.neunet.2025.107855_bib0013","series-title":"2014 IEEE International solid-state circuits conference digest of technical papers (ISSCC)","first-page":"10","article-title":"1.1 Computing\u2019s energy problem (and what we can do about it)","author":"Horowitz","year":"2014"},{"key":"10.1016\/j.neunet.2025.107855_bib0014","unstructured":"Huang, W., Liu, Y., Qin, H., Li, Y., Zhang, S., Liu, X., Magno, M., & Qi, X. (2024a). BiLLM: Pushing the limit of post-training quantization for LLMs. arXiv preprint arXiv:2402.04291."},{"issue":"1","key":"10.1016\/j.neunet.2025.107855_bib0015","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1007\/s44267-024-00070-x","article-title":"An empirical study of LLaMA3 quantization: From LLMs to MLLMs","volume":"2","author":"Huang","year":"2024","journal-title":"Visual Intelligence"},{"key":"10.1016\/j.neunet.2025.107855_bib0016","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2704","article-title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","author":"Jacob","year":"2018"},{"key":"10.1016\/j.neunet.2025.107855_bib0017","unstructured":"Li, F., Liu, B., Wang, X., Zhang, B., & Yan, J. (2016). Ternary weight networks. arXiv preprint arXiv:1605.04711."},{"key":"10.1016\/j.neunet.2025.107855_bib0018","unstructured":"Li, Y., Gong, R., Tan, X., Yang, Y., Hu, P., Zhang, Q., Yu, F., Wang, W., & Gu, S. (2021a). BRECQ: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426."},{"key":"10.1016\/j.neunet.2025.107855_bib0019","unstructured":"Li, Y., Shen, M., Ma, J., Ren, Y., Zhao, M., Zhang, Q., Gong, R., Yu, F., & Yan, J. (2021b). MQBench: Towards reproducible and deployable model quantization benchmark. arXiv preprint arXiv:2111.03759."},{"key":"10.1016\/j.neunet.2025.107855_bib0020","unstructured":"Li, Z., Yan, X., Zhang, T., Qin, H., Xie, D., Tian, J., Kong, L., Zhang, Y., Yang, X. et al. (2024). ARB-LLM: Alternating refined binarizations for large language models. arXiv preprint arXiv:2410.03129."},{"key":"10.1016\/j.neunet.2025.107855_bib0021","unstructured":"Lin, J., Tang, J., Tang, H., Yang, S., Dang, X., & Han, S. (2023). AWQ: Activation-aware weight quantization for LLM compression and acceleration. arXiv preprint arXiv:2306.00978."},{"key":"10.1016\/j.neunet.2025.107855_bib0022","doi-asserted-by":"crossref","unstructured":"Liu, Z., Oguz, B., Zhao, C., Chang, E., Stock, P., Mehdad, Y., Shi, Y., Krishnamoorthi, R., & Chandra, V. (2023). LLM-QAT: Data-free quantization aware training for large language models. arXiv preprint arXiv:2305.17888.","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"10.1016\/j.neunet.2025.107855_bib0023","unstructured":"Ma, S., Wang, H., Ma, L., Wang, L., Wang, W., Huang, S., Dong, L., Wang, R., Xue, J., & Wei, F. (2024). The era of 1-bit LLMs: All large language models are in 1.58 bits. arXiv preprint arXiv: 2402.17764."},{"key":"10.1016\/j.neunet.2025.107855_bib0024","unstructured":"Merity, S., Xiong, C., Bradbury, J., & Socher, R. (2016). Pointer sentinel mixture models. arXiv preprint arXiv: 1609.07843."},{"key":"10.1016\/j.neunet.2025.107855_bib0025","unstructured":"Meta (2024). Introducing Llama 3.1: Our most capable models to date. https:\/\/ai.meta.com\/blog\/meta-llama-3-1\/."},{"key":"10.1016\/j.neunet.2025.107855_bib0026","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L. et al. (2019). PyTorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703."},{"issue":"140","key":"10.1016\/j.neunet.2025.107855_bib0027","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"10.1016\/j.neunet.2025.107855_bib0028","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"issue":"9","key":"10.1016\/j.neunet.2025.107855_bib0029","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3474381","article-title":"WinoGrande: An adversarial winograd schema challenge at scale","volume":"64","author":"Sakaguchi","year":"2021","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.neunet.2025.107855_bib0030","unstructured":"Shang, Y., Yuan, Z., Wu, Q., & Dong, Z. (2023). PB-LLM: Partially binarized large language models. arXiv preprint arXiv:2310.00034."},{"key":"10.1016\/j.neunet.2025.107855_bib0031","unstructured":"Shao, W., Chen, M., Zhang, Z., Xu, P., Zhao, L., Li, Z., Zhang, K., Gao, P., Qiao, Y., & Luo, P. (2023). OmniQuant: Omnidirectionally calibrated quantization for large language models. arXiv preprint arXiv:2308.13137."},{"key":"10.1016\/j.neunet.2025.107855_bib0032","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13693","article-title":"Energy and policy considerations for modern deep learning research","volume":"vol. 34","author":"Strubell","year":"2020"},{"key":"10.1016\/j.neunet.2025.107855_bib0033","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F. et al. (2023a). LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"10.1016\/j.neunet.2025.107855_bib0034","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S. et al. (2023b). LLaMA 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288."},{"key":"10.1016\/j.neunet.2025.107855_bib0035","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107855_bib0036","unstructured":"Wang, H., Ma, S., Dong, L., Huang, S., Wang, H., Ma, L., Yang, F., Wang, R., Wu, Y., & Wei, F. (2023). BitNet: Scaling 1-bit transformers for large language models. arXiv preprint arXiv:2310.11453."},{"key":"10.1016\/j.neunet.2025.107855_bib0037","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, Y., Li, Y., Zhang, X., Gong, R., Guo, J., & Liu, X. (2023). Outlier suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling. arXiv preprint arXiv:2304.09145.","DOI":"10.18653\/v1\/2023.emnlp-main.102"},{"key":"10.1016\/j.neunet.2025.107855_bib0038","first-page":"17402","article-title":"Outlier suppression: Pushing the limit of low-bit transformer language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107855_bib0039","series-title":"International conference on machine learning","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2023"},{"key":"10.1016\/j.neunet.2025.107855_bib0040","unstructured":"Xing, X., Gao, B., Zhang, Z., Clifton, D. A., Xiao, S., Du, L., Li, G., & Zhang, J. (2024a). SpikeLLM: Scaling up spiking neural network to large language models via saliency-based spiking. https:\/\/arxiv.org\/abs\/2407.04752."},{"key":"10.1016\/j.neunet.2025.107855_bib0041","unstructured":"Xing, X., Zhang, Z., Ni, Z., Xiao, S., Ju, Y., Fan, S., Wang, Y., Zhang, J., & Li, G. (2024b). SpikeLM: Towards general spike-driven language modeling via elastic bi-spiking mechanisms. arXiv preprint arXiv:2406.03287."},{"key":"10.1016\/j.neunet.2025.107855_bib0042","series-title":"2019 fifth workshop on energy efficient machine learning and cognitive computing-neurIPS edition (EMC2-NIPS)","first-page":"36","article-title":"Q8BERT: Quantized 8bit bert","author":"Zafrir","year":"2019"},{"key":"10.1016\/j.neunet.2025.107855_bib0043","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X. V. et al. (2022). OPT: Open pre-trained transformer language models. arXiv preprint arXiv: 2205.01068."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802500735X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802500735X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T20:04:52Z","timestamp":1777579492000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802500735X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":43,"alternative-id":["S089360802500735X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107855","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PT-BitNet: Scaling up the 1-Bit large language model with post-training quantization","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107855","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107855"}}