NOTICE:
We have released the Hy-MT2 series of translation models, offering improved performance and excellent instruction-following capabilities. The link to the new model collection is: https://huggingface.co/collections/tencent/hy-mt2
We are excited to announce our official partnership with WMT26. We welcome all participants to use our HY-MT model during the competition. Teams that use HY-MT and achieve notable results will be eligible for cash prizes. For more details, please contact us at hunyuan@tencent.com.
To help you get started with HY-MT training more quickly, we have provided a Training Tutorial. You can access it via the link below.
Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation model, HY-MT1.5-7B. Both models focus on supporting mutual translation across 33 languages and incorporating 5 ethnic and dialect variations. Among them, HY-MT1.5-7B is an upgraded version of our WMT25 championship model, optimized for explanatory translation and mixed-language scenarios, with newly added support for terminology intervention, contextual translation, and formatted translation. Despite having less than one-third the parameters of HY-MT1.5-7B, HY-MT1.5-1.8B delivers translation performance comparable to its larger counterpart, achieving both high speed and high quality. After quantization, the 1.8B model can be deployed on edge devices and support real-time translation scenarios, making it widely applicable.
Key Features and Advantages
HY-MT1.5-1.8B achieves the industry-leading performance among models of the same size, surpassing most commercial translation APIs.
HY-MT1.5-1.8B supports deployment on edge devices and real-time translation scenarios, offering broad applicability.
HY-MT1.5-7B, compared to its September open-source version, has been optimized for annotated and mixed-language scenarios.
Both models support terminology intervention, contextual translation, and formatted translation.
Related News
2025.12.30, we have open-sourced HY-MT1.5-1.8B and HY-MT1.5-7B on Hugging Face.
2025.9.1, we have open-sourced Hunyuan-MT-7B , Hunyuan-MT-Chimera-7B on Hugging Face.
Performance
You can refer to our technical report for more experimental results and analysis.
!!! If you want to load fp8 model with transformers, you need to change the name"ignored_layers" in config.json to "ignore" and upgrade the compressed-tensors to compressed-tensors-0.11.0.
The following code snippet shows how to use the transformers library to load and apply the model.
we use tencent/HY-MT1.5-1.8B for example
python
1from transformers import AutoModelForCausalLM, AutoTokenizer
2import os
34model_name_or_path ="tencent/HY-MT1.5-1.8B"56tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)7model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto")# You may want to use bfloat16 and/or move to GPU here8messages =[9{"role":"user","content":"Translate the following segment into Chinese, without additional explanation.\n\nIt’s on the house."},10]11tokenized_chat = tokenizer.apply_chat_template(12 messages,13 tokenize=True,14 add_generation_prompt=False,15 return_tensors="pt"16)1718outputs = model.generate(tokenized_chat.to(model.device), max_new_tokens=2048)19output_text = tokenizer.decode(outputs[0])
We recommend using the following set of parameters for inference. Note that our model does not have the default system_prompt.
1@misc{hy-mt1.5,
2 title={HY-MT1.5 Technical Report},
3 author={Mao Zheng and Zheng Li and Tao Chen and Mingyang Song and Di Wang},
4 year={2025},
5 eprint={2512.24092},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL},
8 url={https://arxiv.org/abs/2512.24092},
9}
