Seed-X-RM-7B / README.md
YuLu0713's picture
Update README.md
2af2ccc verified
|
raw
history blame
4.6 kB
metadata
license: other
license_name: openmdw
license_link: LICENSE

Seed-X-RM-7B

Introduction

We are excited to introduce Seed-X, a powerful open-source multilingual translation language model series, including instruction and reasoning models, with 7B parameters pushing the boundaries of translation capabilities. We develop Seed-X as an accessible, off-the-shelf tool to support the community in advancing translation research and applications:

  • 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. performance

This repo contains the Seed-X-RM model, with the following features:

  • Type: Causal language models
  • Training Stage: Pretraining & Post-training
  • Data Source: Human preference data on multilingual translation
  • Support: Evaluating translation betweeen 28 languages
Languages Abbr. Languages Abbr. Languages Abbr. Languages Abbr.
Arabic ar French fr Malay ms Russian ru
Czech cs Croatian hr Norwegian Bokmal nb Swedish sv
Danish da Hungarian hu Dutch nl Thai th
German de Indonesian id Norwegian no Turkish tr
English en Italian it Polish pl Ukrainian uk
Spanish es Japanese ja Portuguese pt Vietnamese vi
Finnish fi Korean ko Romanian ro Chinese zh

Model Downloads

Model Name Description Download
Seed-X-Instruct Instruction-tuned for alignment with user intent. 🤗 Model
Seed-X-PPO RL trained to boost translation capabilities. 🤗 Model
👉 Seed-X-RM Reward model to evaluate the quality of translation. 🤗 Model

Quickstart

Seed-X-RM assigns a reward score to the given translation with the same prompt format as Seed-X-PPO.

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. humen_eval For detailed benchmark results and analysis, please refer to our Technical Report.

License

This project is licensed under OpenMDW. See the LICENSE flie 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:

@Article{XXX,
      title={XXXXXXXXXXX}, 
      author={XXX,XXX,XXX,XXX},
      year={2025},
      eprint={XXXX.XXXXX},
      archivePrefix={arXiv},
      primaryClass={cs.XX}
}

We will soon publish our technical report on Arxiv.