Hy-MT2：面向复杂真实场景的快速、高效且强大的多语言翻译模型系列
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
AI总结：
本文提出Hy-MT2系列多语言翻译模型，通过三种规模（1.8B、7B、30B-A3B MoE）支持33种语言翻译，在通用、商业、领域和指令跟随任务上超越开源模型和商业API，并实现轻量级设备端部署。
摘要：
Hy-MT2是一系列面向复杂真实场景的快速思考多语言翻译模型。它包括三种模型规模：1.8B、7B和30B-A3B（MoE），均支持33种语言之间的翻译，并能有效遵循多种语言的翻译指令。多维度评估表明，Hy-MT2在通用、真实世界业务、领域特定和指令跟随翻译任务中均表现出色。7B和30B模型在快速思考模式下超越了DeepSeek-V4-Pro和Kimi K2.6等开源模型，而轻量级的1.8B模型在整体性能上也超越了微软、豆包等提供商的主流商业API。此外，当与AngelSlim的1.25位极端量化结合用于设备端部署时，轻量级1.8B模型仅需440 MB存储空间，并实现了1.5倍的推理加速。
英文摘要：
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages. Multi-dimensional evaluations show that Hy-MT2 delivers outstanding performance across general, real-world business, domain-specific, and instruction-following translation tasks. The 7B and 30B models outperform open-source models such as DeepSeek-V4-Pro and Kimi K2.6 in fast-thinking mode, while the lightweight 1.8B model also surpasses mainstream commercial APIs from providers such as Microsoft and Doubao overall. Moreover, when paired with AngelSlim's 1.25-bit extreme quantization for on-device deployment, the lightweight 1.8B model requires only 440 MB of storage and achieves a 1.5x inference speedup.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
