Hy-MT2是高效多语言翻译模型，支持33种语言实时翻译。
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
- 基于三种规模的混合专家模型，支持33语言互译。
- 7B与30B模型超越DeepSeek-V4-Pro等开源模型性能。
- 1.8B轻量版可部署于设备端，仅需440MB存储且提速1.5倍。
Hy-MT2是一系列专为复杂真实场景设计的快速多语言翻译模型，包含1.8B、7B和30B-A3B（MoE）三种规模，均支持33种语言间的翻译，并能有效遵循多语言翻译指令。多维度评估显示，Hy-MT2在通用、实际业务、领域特定及指令跟随翻译任务中均表现卓越。7B与30B模型在快速推理模式下优于DeepSeek-V4-Pro和Kimi K2.6等开源模型，而轻量级1.8B模型整体性能也超过微软、通义千问等主流商业API。结合AngelSlim的1.25比特极低精度量化技术进行设备端部署时，1.8B模型仅需440 MB存储空间，并实现1.5倍推理加速。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。