模型:
unicamp-dl/mt5-base-mmarco-v2
mt5-base-mmarco-v2是基于mT5模型在多语言翻译版本的MS MARCO段落数据集上进行微调的模型。该数据集名为Multi MS MARCO,由9个不同语言的完整MS MARCO段落集合组成。在v2版本中,使用谷歌翻译对数据集进行了翻译。有关数据集或翻译方法的更多信息可以在我们的论文 mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset 和 mMARCO 的存储库中找到。
from transformers import T5Tokenizer, MT5ForConditionalGeneration model_name = 'unicamp-dl/mt5-base-mmarco-v2' tokenizer = T5Tokenizer.from_pretrained(model_name) model = MT5ForConditionalGeneration.from_pretrained(model_name)
如果您使用了mt5-base-mmarco-v2,请引用:
@misc{bonifacio2021mmarco, title={mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset}, author={Luiz Henrique Bonifacio and Vitor Jeronymo and Hugo Queiroz Abonizio and Israel Campiotti and Marzieh Fadaee and and Roberto Lotufo and Rodrigo Nogueira}, year={2021}, eprint={2108.13897}, archivePrefix={arXiv}, primaryClass={cs.CL}
}