{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T17:13:21Z","timestamp":1778087601657,"version":"3.51.4"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032253101","type":"print"},{"value":"9783032253118","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-25311-8_5","type":"book-chapter","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:40:07Z","timestamp":1778085607000},"page":"60-66","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Parallelising Pre-trained Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8765-604X","authenticated-orcid":false,"given":"Vincenzo","family":"Scotti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6575-9737","authenticated-orcid":false,"given":"Mark James","family":"Carman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"5_CR1","unstructured":"Chowdhery, A., Narang, S., Devlin, J., et\u00a0al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24, 240:1\u2013240:113 (2023)"},{"key":"5_CR2","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., et\u00a0al.: Universal transformers. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019)"},{"key":"5_CR3","unstructured":"Del\u00e9tang, G., Ruoss, A., Duquenne, P., et\u00a0al.: Language modeling is compression. CoRR arxiv:2309.10668 (2023)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., et\u00a0al.: Qlora: efficient finetuning of quantized LLMs. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, 10\u201316 December 2023 (2023)","DOI":"10.52202\/075280-0441"},{"key":"5_CR5","unstructured":"Gao, L., Tow, J., Abbasi, B., et\u00a0al.: A framework for few-shot language model evaluation (2023)"},{"key":"5_CR6","unstructured":"Gokaslan, A., Cohen, V.: Openwebtext corpus (2019)"},{"key":"5_CR7","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., et\u00a0al.: Mistral 7b. CoRR arxiv:2310.06825 (2023)"},{"key":"5_CR8","unstructured":"Kojima, T., Gu, S.S., Reid, M., et\u00a0al.: Large language models are zero-shot reasoners. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, 28 November\u20139 December 2022 (2022)"},{"key":"5_CR9","unstructured":"Merity, S., Xiong, C., Bradbury, J., et\u00a0al.: Pointer sentinel mixture models. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings. OpenReview.net (2017)"},{"key":"5_CR10","unstructured":"Mesnard, T., Hardin, C., Dadashi, R., et\u00a0al.: Gemma: open models based on gemini research and technology. CoRR arxiv:2403.08295 (2024)"},{"key":"5_CR11","unstructured":"Meta Llama: Introducing meta llama 3: The most capable openly available LLM to date (2024)"},{"key":"5_CR12","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4\u20139 December 2017, pp. 5998\u20136008 (2017)"},{"key":"5_CR13","unstructured":"Wolf, T., Debut, L., Sanh, V., et\u00a0al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. CoRR arxiv:1910.03771 (2019)"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-25311-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:40:14Z","timestamp":1778085614000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-25311-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032253101","9783032253118"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-25311-8_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}