Randeng Deltalm 362M En Zh

🚀 Randeng-Deltalm-362M-En-Zh

A translation model for English to Chinese based on the Fengshen-LM framework.

• Main Page: Fengshenbang
• Github: Fengshenbang-LM

🚀 Quick Start

This model is fine-tuned on the Detalm base using the Fengshen-LM framework. It is trained on a collected English-Chinese dataset (30 million entries in total) and the English-Chinese parallel data from IWSLT (200,000 entries), resulting in a translation model for the English -> Chinese direction.

✨ Features

Model Taxonomy

Model Information

Reference Paper: DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders

Performance

💻 Usage Examples

Basic Usage

# Need to download modeling_deltalm.py from Fengshenbang-LM github repo in advance,
# or you can download modeling_deltalm.py use wget https://huggingface.co/IDEA-CCNL/Randeng-Deltalm-362M-En-Zn/resolve/main/modeling_deltalm.py
# Strongly recommend you git clone the Fengshenbang-LM repo:
# 1. git clone https://github.com/IDEA-CCNL/Fengshenbang-LM
# 2. cd Fengshenbang-LM/fengshen/

from models.deltalm.modeling_deltalm import DeltalmForConditionalGeneration
from transformers import AutoTokenizer

model = DeltalmForConditionalGeneration.from_pretrained("IDEA-CCNL/Randeng-Deltalm-362M-En-Zn")
tokenizer = AutoTokenizer.from_pretrained("microsoft/infoxlm-base")

text = "In summer, especially, you'll need to watch out for mosquitoes if you decide to hike through the rainforest."
inputs = tokenizer(text, max_length=512, return_tensors="pt")

generate_ids = model.generate(inputs["input_ids"], max_length=512)
tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]

# model Output:
# 如果你决定徒步穿越热带雨林,你需要小心蚊子,尤其是在夏天。

📄 License

Citation

If you are using the resource for your work, please cite our paper:

@article{fengshenbang,
  author    = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen},
  title     = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
  journal   = {CoRR},
  volume    = {abs/2209.02970},
  year      = {2022}
}

You can also cite our website:

@misc{Fengshenbang-LM,
  title={Fengshenbang-LM},
  author={IDEA-CCNL},
  year={2021},
  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}