Hy-MT2-7B

English ｜ 中文

[](https://huggingface.co/collections/tencent/hy-mt2)

  

[](https://modelscope.cn/collections/Tencent-Hunyuan/Hy-MT2)

🖥️ Official Website     

💬 GitHub     

🪡 AngelSlim     

📚 Hy-MT2 Report

Model Introduction

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.

For on-device deployment, AngelSlim 1.25-bit extreme quantization reduces the storage requirement of the 1.8B model to only 440 MB and improves inference speed by 1.5x.

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-A3B 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.

In this release, we also open-source IFMTBench, a benchmark for evaluating translation instruction-following capabilities.

We also welcome everyone to use our released Hy-MT2-Translator Skill, which makes it easy to integrate Hy-MT2 series models for translation tasks. Download links: ClawHub and SkillHub.

Now, Tencent Hy is officially partnering with WMT26 for the "Video Subtitle Translation Task" (https://www2.statmt.org/wmt26/video-subtitle-translation.html). Participants who use the Hy-MT model series to compete in the "General Machine Translation Task" (https://www2.statmt.org/wmt26/translation-task.html) and the "Video Subtitle Translation Task" will have the chance to win special awards sponsored by Hunyuan. We sincerely invite everyone to participate and jointly push the boundaries of machine translation technology!

News

• 5.21 We open-sourced **Hy-MT2-1.8B**/**Hy-MT2-7B**/**Hy-MT2-30B-A3B**/**IFMTBench** on HuggingFace and ModelScope.
• 12.30 We open-sourced **HY-MT1.5-1.8B** and **HY-MT1.5-7B** on HuggingFace and ModelScope.
• 9.1 We open-sourced **Hunyuan-MT-7B** and **Hunyuan-MT-Chimera-7B** on HuggingFace and ModelScope.

Results

For more experimental results and analysis, please refer to our report.

 

Model Links

Model Name Description Download Link

• ---------- ----------- -----------

Hy-MT2-1.8B Hy 1.8B translation model 🤗 Model

Hy-MT2-1.8B-FP8 Hy 1.8B translation model, FP8 quantization 🤗 Model

Hy-MT2-1.8B-GGUF Hy 1.8B translation model, llama.cpp 🤗 Model

Hy-MT2-1.8B-2bit-GGUF Hy 1.8B translation model, llama.cpp, 2bit 🤗 Model

Hy-MT2-1.8B-1.25bit-GGUF Hy 1.8B translation model, llama.cpp, 1.25bit 🤗 Model

Hy-MT2-7B Hy 7B translation model 🤗 Model

Hy-MT2-7B-FP8 Hy 7B translation model, FP8 quantization 🤗 Model

Hy-MT2-7B-GGUF Hy 7B translation model, llama.cpp 🤗 Model

Hy-MT2-30B-A3B Hy 30B-A3B translation model 🤗 Model

Hy-MT2-30B-A3B-FP8 Hy 30B-A3B translation model, FP8 quantization 🤗 Model

Hy-MT2 Translation Task Instruction Examples (Chinese-English Comparison)

Note: In the following examples, both source lang and target lang should use the full language names. Chinese names should be used in Chinese prompts, and English names should be used in English prompts.*

Type Chinese prompt English prompt

• -- --- ---
• *Default Translation** 将以下文本翻译为 {target lang} ，注意**只需要输出翻译后的结果，不要额外解释**： {source text} Translate the following text into {target lang} . Note that you should **only output the translated result without any additional explanation**: {source text}
• *Terminology** *参考下面的翻译：* {text} 翻译成 {text} {text} 翻译成 {text} {text} 翻译成 {text} 将以下文本翻译为 {target lang} ，注意**只需要输出翻译后的结果，不要额外解释**： {source text} *Reference the following translations:* {text} translates to {text} {text} translates to {text} {text} translates to {text} Translate the following text into {target lang} . Note that you must **ONLY output the translated result without any additional explanation**: {source text}
• *Style** 请将以下文本翻译为 {target lang} 。注意翻译的风格要严格符合【** {target style} **】 {source text} Please translate the following text into {target lang} . Note that the translation style must strictly conform to [** {target style} **]: {source text}
• *Personalization** *【待翻译文本】* {source text} *【翻译任务】*1、** {user preferences} **2、** {user preferences} **3、……4、将【待翻译文本】翻译为 {target lang} 。 *[Source Text]* {source text} *[Translation Tasks]*1. ** {user preferences} **2. ** {user preferences} **3. ...4. Translate the [Source Text] into {target lang} .
• *Delimiters** 请将以下文本准确翻译为 {target lang} 。你必须在译文中**保留等量的分隔符，绝对不可遗漏、转义或翻译该符号，并注意分隔符的位置**。 {source text} Please accurately translate the following text into {target lang} .You must **retain the exact same number of delimiters in the translation. Strictly do not omit, escape, or translate these symbols, and pay close attention to their placement**. {source text}
• *Structured Data 1** *# 任务目标*将下方 {source text} 中的 {format type} 格式数据翻译为 {target lang} 。*# 严格约束*1. **结构锁定**：绝对保持原有的 {format type} 数据结构、缩进和层级完全不变。2. **选择性翻译**：仅翻译面向用户展示的可见文本内容。3. **禁止修改**：**严禁**翻译或更改任何代码标签、键名 (Key)、变量占位符（如 {{var}} 、 ${var} 、 %s 、 %d 等）或代码属性。*# 数据输入* {source text} *### Task*Translate the user-facing text within the following {format type} data into {target lang} .*### Strict Rules*1. **Structure Preservation:** You MUST preserve the original {format type} data structure, nesting, hierarchy, and indentation exactly as they are.2. **Selective Translation:** Translate ONLY the visible, user-facing text content/values.3. **Strict Non-Translation:** NEVER translate or alter code tags, keys, properties, object names, or variable placeholders. Leave them exactly in their original English/code form.*### Source Data* {source text}
• *Structured Data 2** *【背景信息】* {background text} 请结合背景信息将以下文本翻译为 {target lang} 。*【待翻译文本】* {source text} *[Background Information]* {background text} Please translate the following text into {target lang} , taking the provided background information into consideration.*[Source Text]* {source text}

Inference and Deployment

For 1.8B and 7B, we recommend using the following parameters for inference. Note that our models do not have a default system prompt.

For 30B-A3B, we recommend using the following parameters for inference. Note that our models do not have a default system prompt.

transformers

transformers>=5.6.0

vllm

Build vLLM from source:

Start the vLLM server:

sglang

Build SGLang from source:

Launch SGLang server:

llama cpp

❕❕ This gguf depends on our STQ kernel, which is released at PR #22836.**

Clone llama.cpp

Enter the llama.cpp folder

Build llama.cpp

Run a completion example

Run the llama.cpp benchmark

Model Training

Hy-MT2 provides a complete model training pipeline, supporting both full-parameter fine-tuning and LoRA fine-tuning, as well as multiple DeepSpeed ZeRO configurations and LLaMA-Factory integration.

For detailed training documentation, please refer to: Model Training Guide

Quantization Tool

We provide AngelSlim, an easy-to-use, comprehensive, and efficient large model compression toolkit covering common quantization algorithms, low-bit quantization, speculative sampling, and more.

Supported Languages

Languages Abbr. Chinese Names

• ------------------ --------- -----------------

Chinese zh 中文

English en 英语

French fr 法语

Portuguese pt 葡萄牙语

Spanish es 西班牙语

Japanese ja 日语

Turkish tr 土耳其语

Russian ru 俄语

Arabic ar 阿拉伯语

Korean ko 韩语

Thai th 泰语

Italian it 意大利语

German de 德语

Vietnamese vi 越南语

Malay ms 马来语

Indonesian id 印尼语

Filipino tl 菲律宾语

Hindi hi 印地语

Traditional Chinese zh-Hant 繁体中文

Polish pl 波兰语

Czech cs 捷克语

Dutch nl 荷兰语

Khmer km 高棉语

Burmese my 缅甸语

Persian fa 波斯语

Gujarati gu 古吉拉特语

Urdu ur 乌尔都语

Telugu te 泰卢固语

Marathi mr 马拉地语

Hebrew he 希伯来语

Bengali bn 孟加拉语

Tamil ta 泰米尔语

Ukrainian uk 乌克兰语

Tibetan bo 藏语

Kazakh kk 哈萨克语

Mongolian mn 蒙古语

Uyghur ug 维吾尔语

Cantonese yue 粤语

Citing Hy-MT2

Contact Us

If you would like to leave feedback for our R&D and product teams, you are welcome to contact the Tencent Hunyuan LLM team. You can reach us by email at hunyuan opensource@tencent.com.