模型:
unicamp-dl/mMiniLM-L6-v2-mmarco-v2
mMiniLM-L6-v2-mmarco-v2是基于多语言miniLM模型在多语言版本MS MARCO段落数据集上进行微调的模型。该数据集名为mMARCO,由9种不同语言的段落组成,这些段落是从英文MS MARCO段落集合翻译而来。在v2版本中,使用Google Translate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 mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset 和 mMARCO 存储库中找到。
from transformers import AutoTokenizer, AutoModel model_name = 'unicamp-dl/mMiniLM-L6-v2-mmarco-v2' tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModel.from_pretrained(model_name)
如果您使用mMiniLM-L6-v2-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}
}