Download
Hy-MT2 is a family of fast-thinking multilingual translation models built for complex real-world translation scenarios. It includes 1.8B, 7B, and 30B-A3B model sizes, giving users options for lightweight deployment, stronger general performance, or MoE-based capacity. The models support translation across 33 languages and are designed to follow detailed translation instructions in multiple languages. They can handle tasks involving terminology, style, personalization, delimiters, structured data, and background-aware translation. The repository also provides model links, inference guidance, deployment examples, training documentation, and quantization resources. Overall, Hy-MT2 is useful for developers and researchers who need flexible, instruction-following machine translation models for production, evaluation, or experimentation.
Features
- Fast-thinking multilingual translation model family
- 1.8B, 7B, and 30B-A3B model options
- Translation support across 33 languages
- Instruction-following translation for terminology, style, and structured data
- Inference support through transformers, vLLM, SGLang, and llama.cpp
- Training pipeline, LoRA fine-tuning, and quantization resources
Project Samples
