Sponsored by
Tripo AI
tencent / Hunyuan-MT-7B
Model's Last Updated: December 30 2025
translation
Introduction of Hunyuan-MT-7B
Model Details of Hunyuan-MT-7B
🤗
Hugging Face
|
🖥️ Official Website | 🕹️ Demo
Model Introduction
The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera. The translation model is used to translate source text into the target language, while the ensemble model integrates multiple translation outputs to produce a higher-quality result. It primarily supports mutual translation among 33 languages, including five ethnic minority languages in China.
Key Features and Advantages
- In the WMT25 competition, the model achieved first place in 30 out of the 31 language categories it participated in.
- Hunyuan-MT-7B achieves industry-leading performance among models of comparable scale
- Hunyuan-MT-Chimera-7B is the industry’s first open-source translation ensemble model, elevating translation quality to a new level
- A comprehensive training framework for translation models has been proposed, spanning from pretrain → cross-lingual pretraining (CPT) → supervised fine-tuning (SFT) → translation enhancement → ensemble refinement, achieving state-of-the-art (SOTA) results for models of similar size
Related News
-
2025.9.1 We have open-sourced
Hunyuan-MT-7B
,
Hunyuan-MT-Chimera-7B
on Hugging Face.
模型链接
| Model Name | Description | Download |
|---|---|---|
| Hunyuan-MT-7B | Hunyuan 7B translation model | 🤗 Model |
| Hunyuan-MT-7B-fp8 | Hunyuan 7B translation model，fp8 quant | 🤗 Model |
| Hunyuan-MT-Chimera | Hunyuan 7B translation ensemble model | 🤗 Model |
| Hunyuan-MT-Chimera-fp8 | Hunyuan 7B translation ensemble model，fp8 quant | 🤗 Model |
Prompts
Prompt Template for ZH<=>XX Translation.
把下面的文本翻译成
<target_language>
，不要额外解释。
<source_text>
Prompt Template for XX<=>XX Translation, excluding ZH<=>XX.
Translate the following segment into
<target_language>
, without additional explanation.
<source_text>
Prompt Template for Hunyuan-MT-Chmeria-7B
Analyze the following multiple
<target_language>
translations of the
<source_language>
segment surrounded in triple backticks and generate a single refined
<target_language>
translation. Only output the refined translation, do not explain.
The
<source_language>
segment:
<source_text>
The multiple
<target_language>
translations:
-
<translated_text1> -
<translated_text2> -
<translated_text3> -
<translated_text4> -
<translated_text5> -
<translated_text6>
Use with transformers
First, please install transformers, recommends v4.55.4
pip install transformers==4.55.4
The following code snippet shows how to use the transformers library to load and apply the model.
we use tencent/Hunyuan-MT-7B for example
from transformers import AutoModelForCausalLM, AutoTokenizer
import os
model_name_or_path = "tencent/Hunyuan-MT-7B"
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.
{
"top_k": 20,
"top_p": 0.6,
"repetition_penalty": 1.05,
"temperature": 0.7
}
Runs of tencent Hunyuan-MT-7B on huggingface.co
3.0K
Total runs
0
24-hour runs
254
3-day runs
317
7-day runs
-136
30-day runs
More Information About Hunyuan-MT-7B huggingface.co Model
Url of Hunyuan-MT-7B
Hunyuan-MT-7B huggingface.co Url
Provider of Hunyuan-MT-7B huggingface.co
Other API from tencent
Total runs:
360.4K
Run Growth:
310.7K
Growth Rate:
87.32%
Total runs:
98.7K
Run Growth:
-32.1K
Growth Rate:
-32.77%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
55.0K
Run Growth:
-3.2K
Growth Rate:
-5.79%
Total runs:
49.8K
Run Growth:
22.0K
Growth Rate:
48.13%
Total runs:
47.0K
Run Growth:
1.1K
Growth Rate:
2.49%
Total runs:
39.8K
Run Growth:
39.1K
Growth Rate:
98.30%
Total runs:
30.1K
Run Growth:
4.1K
Growth Rate:
13.72%
Total runs:
18.2K
Run Growth:
18.2K
Growth Rate:
100.00%
Total runs:
18.1K
Run Growth:
-11.3K
Growth Rate:
-61.33%
Total runs:
17.4K
Run Growth:
9.2K
Growth Rate:
53.10%
Total runs:
13.7K
Run Growth:
11.4K
Growth Rate:
83.54%
Total runs:
12.8K
Run Growth:
-17.0K
Growth Rate:
-139.16%
Total runs:
10.2K
Run Growth:
988
Growth Rate:
10.82%
Total runs:
7.3K
Run Growth:
-1.6K
Growth Rate:
-21.77%
Total runs:
5.6K
Run Growth:
5.6K
Growth Rate:
100.00%
Total runs:
5.4K
Run Growth:
5.4K
Growth Rate:
100.00%
Total runs:
5.2K
Run Growth:
-1.5K
Growth Rate:
-28.75%
Total runs:
4.4K
Run Growth:
-1.2K
Growth Rate:
-27.38%
Total runs:
4.0K
Run Growth:
-609
Growth Rate:
-15.23%
Total runs:
3.4K
Run Growth:
1.8K
Growth Rate:
88.79%
Total runs:
3.2K
Run Growth:
-919
Growth Rate:
-29.42%
Total runs:
2.8K
Run Growth:
2.3K
Growth Rate:
80.50%
Total runs:
2.7K
Run Growth:
-18.0K
Growth Rate:
-905.23%
Total runs:
2.6K
Run Growth:
2.6K
Growth Rate:
100.00%
Total runs:
2.2K
Run Growth:
2.0K
Growth Rate:
92.72%
Total runs:
1.8K
Run Growth:
327
Growth Rate:
17.71%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.6K
Run Growth:
-956
Growth Rate:
-59.79%
Total runs:
1.6K
Run Growth:
361
Growth Rate:
22.45%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.1K
Run Growth:
591
Growth Rate:
59.22%
Total runs:
1.0K
Run Growth:
611
Growth Rate:
60.20%
Total runs:
992
Run Growth:
755
Growth Rate:
76.81%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
589
Run Growth:
-489
Growth Rate:
-79.64%
Total runs:
552
Run Growth:
-1.7K
Growth Rate:
-301.45%
Total runs:
549
Run Growth:
197
Growth Rate:
34.02%
Total runs:
540
Run Growth:
79
Growth Rate:
14.71%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
459
Run Growth:
61
Growth Rate:
14.63%
Total runs:
445
Run Growth:
260
Growth Rate:
59.23%
Total runs:
427
Run Growth:
113
Growth Rate:
26.90%
Total runs:
418
Run Growth:
418
Growth Rate:
100.00%
Total runs:
402
Run Growth:
51
Growth Rate:
12.85%
Total runs:
389
Run Growth:
-106
Growth Rate:
-65.03%
Total runs:
382
Run Growth:
316
Growth Rate:
78.61%
Total runs:
337
Run Growth:
-128
Growth Rate:
-38.32%
Total runs:
317
Run Growth:
-81
Growth Rate:
-25.55%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
288
Run Growth:
172
Growth Rate:
59.52%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
274
Run Growth:
-977
Growth Rate:
-359.19%
Total runs:
265
Run Growth:
11
Growth Rate:
4.42%
Total runs:
234
Run Growth:
-381
Growth Rate:
-166.38%
Total runs:
223
Run Growth:
-67
Growth Rate:
-40.12%
Total runs:
220
Run Growth:
-65
Growth Rate:
-30.95%
Total runs:
217
Run Growth:
40
Growth Rate:
19.70%
Total runs:
199
Run Growth:
-59
Growth Rate:
-29.95%
Total runs:
199
Run Growth:
16
Growth Rate:
8.70%
Total runs:
193
Run Growth:
40
Growth Rate:
21.74%
Total runs:
183
Run Growth:
128
Growth Rate:
67.72%
Total runs:
179
Run Growth:
2
Growth Rate:
1.12%
Total runs:
170
Run Growth:
112
Growth Rate:
67.07%
Total runs:
162
Run Growth:
44
Growth Rate:
26.35%