Seed X PPO 7B

🚀 Seed-X-PPO-7B

Seed-X-PPO-7B is a powerful open - source multilingual translation language model. It's part of the Seed - X series, which includes an instruction model, a reinforcement learning model, and a reward model. This model breaks the limits of translation capabilities within 7 billion parameters, offering high - quality translation services across 28 languages.

🚀 Quick Start

📮 Important Note

⚠️ Important Note

• The language tags at the end of the prompt is necessary, which are used in PPO training. For example, when the target language is German, <de> needs to be added. You can refer to the above table for language abbreviations.
• This model is specialized in multilingual translation, which is unexpected to support other tasks.
• We don't have any chat template, thus you don't have to perform tokenizer.apply_chat_template. Please avoid prompting the model in a multi - round conversation format.
• We recommend against using unofficial quantized versions for local deployment. We will soon release an official quantized model and develop a demo on Hugging Face Space.

Here is a simple example demonstrating how to load the model and perform translation using vllm

Recommended:vllm==0.8.0, transformers==4.51.3

from vllm import LLM, SamplingParams, BeamSearchParams

model_path = "./ByteDance-Seed/Seed-X-PPO-7B"

model = LLM(model=model_path,
            max_num_seqs=512,
            tensor_parallel_size=8,
            enable_prefix_caching=True, 
            gpu_memory_utilization=0.95)

messages = [
    # without CoT
    "Translate the following English sentence into Chinese:\nMay the force be with you <zh>",
    # with CoT
    "Translate the following English sentence into Chinese and explain it in detail:\nMay the force be with you <zh>" 
]

# Beam search (We recommend using beam search decoding)
decoding_params = BeamSearchParams(beam_width=4,
                                   max_tokens=512)
# Greedy decoding
decoding_params = SamplingParams(temperature=0,
                                 max_tokens=512,
                                 skip_special_tokens=True)

results = model.generate(messages, decoding_params)
responses = [res.outputs[0].text.strip() for res in results]

print(responses)

✨ Features

• Exceptional translation capabilities: Seed - X exhibits state - of - the - art translation capabilities, on par with or outperforming ultra - large models like Gemini - 2.5, Claude - 3.5, and GPT - 4, as validated by human evaluations and automatic metrics.
• Deployment and inference - friendly: With a compact 7B parameter count and mistral architecture, Seed - X offers outstanding translation performance in a lightweight and efficient package, ideal for deployment and inference.
• Broad domain coverage: Seed - X excels on a highly challenging translation test set spanning diverse domains, including the internet, science and technology, office dialogues, e - commerce, biomedicine, finance, law, literature, and entertainment.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

from vllm import LLM, SamplingParams, BeamSearchParams

model_path = "./ByteDance-Seed/Seed-X-PPO-7B"

model = LLM(model=model_path,
            max_num_seqs=512,
            tensor_parallel_size=8,
            enable_prefix_caching=True, 
            gpu_memory_utilization=0.95)

messages = [
    # without CoT
    "Translate the following English sentence into Chinese:\nMay the force be with you <zh>",
    # with CoT
    "Translate the following English sentence into Chinese and explain it in detail:\nMay the force be with you <zh>" 
]

# Beam search (We recommend using beam search decoding)
decoding_params = BeamSearchParams(beam_width=4,
                                   max_tokens=512)
# Greedy decoding
decoding_params = SamplingParams(temperature=0,
                                 max_tokens=512,
                                 skip_special_tokens=True)

results = model.generate(messages, decoding_params)
responses = [res.outputs[0].text.strip() for res in results]

print(responses)

📚 Documentation

Supported Languages

Model Downloads

Evaluation

We evaluated Seed - X on a diverse set of translation benchmarks, including FLORES - 200, WMT - 25, and a publicly released challenge set accompanied by human evaluations. For detailed benchmark results and analysis, please refer to our Technical Report.

📄 License

This project is licensed under OpenMDW. See the LICENSE file for details.

📚 Citation

If you find Seed - X useful for your research and applications, feel free to give us a star ⭐ or cite us using:

@misc{cheng2025seedxbuildingstrongmultilingual,
      title={Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters}, 
      author={Shanbo Cheng and Yu Bao and Qian Cao and Luyang Huang and Liyan Kang and Zhicheng Liu and Yu Lu and Wenhao Zhu and Jingwen Chen and Zhichao Huang and Tao Li and Yifu Li and Huiying Lin and Sitong Liu and Ningxin Peng and Shuaijie She and Lu Xu and Nuo Xu and Sen Yang and Runsheng Yu and Yiming Yu and Liehao Zou and Hang Li and Lu Lu and Yuxuan Wang and Yonghui Wu},
      year={2025},
      eprint={2507.13618},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2507.13618}, 
}