Sponsored by
APIMart
tencent / Hunyuan-MT-7B-fp8
Model's Last Updated: September 02 2025
translation
Introduction of Hunyuan-MT-7B-fp8
Model Details of Hunyuan-MT-7B-fp8
🤗
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-fp8 on huggingface.co
176
Total runs
0
24-hour runs
-9
3-day runs
-12
7-day runs
-243
30-day runs
More Information About Hunyuan-MT-7B-fp8 huggingface.co Model
Url of Hunyuan-MT-7B-fp8
Hunyuan-MT-7B-fp8 huggingface.co Url
Provider of Hunyuan-MT-7B-fp8 huggingface.co
Other API from tencent
Total runs:
850.5K
Run Growth:
778.2K
Growth Rate:
95.15%
Total runs:
298.4K
Run Growth:
-78.9K
Growth Rate:
-26.32%
Total runs:
149.6K
Run Growth:
46.6K
Growth Rate:
31.63%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
74.1K
Run Growth:
17.9K
Growth Rate:
24.63%
Total runs:
69.9K
Run Growth:
15.9K
Growth Rate:
22.63%
Total runs:
44.4K
Run Growth:
11.9K
Growth Rate:
27.16%
Total runs:
41.3K
Run Growth:
21.8K
Growth Rate:
55.00%
Total runs:
38.2K
Run Growth:
18.7K
Growth Rate:
56.01%
Total runs:
24.5K
Run Growth:
12.6K
Growth Rate:
53.62%
Total runs:
20.3K
Run Growth:
3.2K
Growth Rate:
16.60%
Total runs:
16.5K
Run Growth:
6.5K
Growth Rate:
40.41%
Total runs:
15.9K
Run Growth:
-3.1K
Growth Rate:
-19.78%
Total runs:
15.9K
Run Growth:
-6.4K
Growth Rate:
-40.57%
Total runs:
13.5K
Run Growth:
-37.4K
Growth Rate:
-271.10%
Total runs:
6.1K
Run Growth:
6.1K
Growth Rate:
100.00%
Total runs:
5.2K
Run Growth:
2.2K
Growth Rate:
42.96%
Total runs:
4.6K
Run Growth:
1.5K
Growth Rate:
32.98%
Total runs:
4.5K
Run Growth:
-2.4K
Growth Rate:
-52.45%
Total runs:
3.8K
Run Growth:
3.2K
Growth Rate:
84.18%
Total runs:
3.4K
Run Growth:
1.3K
Growth Rate:
38.92%
Total runs:
3.0K
Run Growth:
-20.2K
Growth Rate:
-683.74%
Total runs:
2.7K
Run Growth:
1.0K
Growth Rate:
37.77%
Total runs:
2.2K
Run Growth:
1.7K
Growth Rate:
76.51%
Total runs:
2.0K
Run Growth:
-47.3K
Growth Rate:
-2348.26%
Total runs:
1.8K
Run Growth:
327
Growth Rate:
17.71%
Total runs:
1.8K
Run Growth:
-2.1K
Growth Rate:
-107.37%
Total runs:
1.8K
Run Growth:
-890
Growth Rate:
-49.44%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.6K
Run Growth:
-129
Growth Rate:
-8.84%
Total runs:
1.6K
Run Growth:
-1.5K
Growth Rate:
-94.90%
Total runs:
1.6K
Run Growth:
1.2K
Growth Rate:
100.00%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.4K
Run Growth:
954
Growth Rate:
70.10%
Total runs:
1.3K
Run Growth:
-273
Growth Rate:
-20.78%
Total runs:
1.3K
Run Growth:
-2.3K
Growth Rate:
-168.68%
Total runs:
1.1K
Run Growth:
-41.4K
Growth Rate:
-3572.04%
Total runs:
1.0K
Run Growth:
34
Growth Rate:
3.34%
Total runs:
958
Run Growth:
496
Growth Rate:
52.10%
Total runs:
824
Run Growth:
188
Growth Rate:
22.82%
Total runs:
809
Run Growth:
-1.8K
Growth Rate:
-220.52%
Total runs:
770
Run Growth:
323
Growth Rate:
42.84%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
675
Run Growth:
201
Growth Rate:
29.69%
Total runs:
674
Run Growth:
323
Growth Rate:
48.94%
Total runs:
640
Run Growth:
298
Growth Rate:
46.71%
Total runs:
620
Run Growth:
97
Growth Rate:
15.62%
Total runs:
604
Run Growth:
-468
Growth Rate:
-76.22%
Total runs:
570
Run Growth:
-1.7K
Growth Rate:
-292.98%
Total runs:
564
Run Growth:
173
Growth Rate:
29.47%
Total runs:
555
Run Growth:
-118
Growth Rate:
-21.69%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
463
Run Growth:
132
Growth Rate:
27.67%
Total runs:
453
Run Growth:
-35
Growth Rate:
-7.73%
Total runs:
422
Run Growth:
188
Growth Rate:
45.85%
Total runs:
399
Run Growth:
89
Growth Rate:
22.65%
Total runs:
373
Run Growth:
150
Growth Rate:
39.89%
Total runs:
331
Run Growth:
187
Growth Rate:
57.19%
Total runs:
319
Run Growth:
119
Growth Rate:
36.84%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
289
Run Growth:
72
Growth Rate:
24.91%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
280
Run Growth:
-185
Growth Rate:
-63.36%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
264
Run Growth:
67
Growth Rate:
25.57%
Total runs:
256
Run Growth:
68
Growth Rate:
27.53%
Total runs:
229
Run Growth:
44
Growth Rate:
19.21%
Total runs:
223
Run Growth:
223
Growth Rate:
100.00%
Total runs:
222
Run Growth:
-2
Growth Rate:
-0.90%