Training tutorial

https://github.com/Tencent-Hunyuan/HY-MT?tab=readme-ov-file#train-with-llama-factory

Model Introduction

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

Technical Report

 

Model Links

Prompts

Prompt Template for ZH<=>XX Translation.

---

markdown
Copy code
将以下文本翻译为{target_language}，注意只需要输出翻译后的结果，不要额外解释：

{source_text}

---

Prompt Template for XX<=>XX Translation, excluding ZH<=>XX.

---

markdown
Copy code
Translate the following segment into {target_language}, without additional explanation.

{source_text}

---

Prompt Template for terminology intervention.

---

markdown
Copy code
参考下面的翻译：
{source_term} 翻译成 {target_term}

将以下文本翻译为{target_language}，注意只需要输出翻译后的结果，不要额外解释：
{source_text}

---

Prompt Template for contextual translation.

---

markdown
Copy code
{context}
参考上面的信息，把下面的文本翻译成{target_language}，注意不需要翻译上文，也不要额外解释：
{source_text}

---

Prompt Template for formatted translation.

---

markdown
Copy code
将以下<source></source>之间的文本翻译为中文，注意只需要输出翻译后的结果，不要额外解释，原文中的<sn></sn>标签表示标签内文本包含格式信息，需要在译文中相应的位置尽量保留该标签。输出格式为：<target>str</target>

<source>{src_text_with_format}</source>

---

 

Use with transformers

First, please install transformers, recommends v4.56.0

SHELL
Copy code
pip install transformers==4.56.0

!!! 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
Copy code
from transformers import AutoModelForCausalLM, AutoTokenizer
import os

model_name_or_path = "tencent/HY-MT1.5-1.8B"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto")  # You may want to use bfloat16 and/or move to GPU here
messages = [
    {"role": "user", "content": "Translate the following segment into Chinese, without additional explanation.\n\nIt’s on the house."},
]
tokenized_chat = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=False,
    return_tensors="pt"
)

outputs = model.generate(tokenized_chat.to(model.device), max_new_tokens=2048)
output_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.

json
Copy code
{
  "top_k": 20,
  "top_p": 0.6,
  "repetition_penalty": 1.05,
  "temperature": 0.7
}

 

Supported languages:

Citing HY-MT1.5:

bibtex
Copy code
@misc{hy-mt1.5,
      title={HY-MT1.5 Technical Report}, 
      author={Mao Zheng and Zheng Li and Tao Chen and Mingyang Song and Di Wang},
      year={2025},
      eprint={2512.24092},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2512.24092}, 
}