YUAN 2.0: A Large Language Model with Localized Filtering-based Attention · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2311.15786/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTYUAN 2.0: A Large Language Model with Localized Filtering-based Attention — mentioned by genidoihttps://news.ycombinator.com/item?id=38539755urn:hackerpapers:mention:2311.15786:38539755Wed, 06 Dec 2023 02:15:52 GMT<p>It was made to be small out of necessity. The US government put extensive export controls on many inter-GPU connectivity products last year and expanded those controls recently to include anything above an A100. Page 9 of this recently published paper[1] is a strong indicator of how far non-US firms go to formally analyze and factor in these bandwidth constraints in building large models. [1] https://arxiv.org/pdf/2311.15786v2.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/2311.15786/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL