Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Report on the Hunyuan-TurboS hybrid Transformer-Mamba model by the Tencent Hunyuan Team; cited at arXiv version 1 of 21 May 2025.
- Issued by
- Tencent / 腾讯
- Authors credited
- No authorship claim recorded yet. The source record lists Tencent Hunyuan Team.
- Dates
- Published 2025-05-21 issue evidence
- Exact source
- Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought arXiv · published 2025-05-21 · Dated document, retrieved on 2026-10-29 (SHA-256 4c9afd472214bfccb1b9b35978f157fba79ebfde949d076256316659599329ca) directly from the publisher. Version: 2505.15431v1. Version 1 as submitted on 21 May 2025 (the title page prints 2025-05-23); versions 2 and 3 not inspected.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
- Issued by: Tencent / 腾讯Tencent's Hunyuan Team posted the Hunyuan-TurboS technical report to arXiv on 21 May 2025 (version 1), describing a hybrid Transformer-Mamba mixture-of-experts model with 56 billion activated and 560 billion total parameters.2025-05-21 · publication · Stated in source · Supported Inspect claim & evidence ↗Tencent / 腾讯: institution →
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.