language: is widget:

• text: "今晚我能请你吗？"
• text: "总统非常出色。"
• text: "这汤的味道。" tags:
• roberta
• 冰岛语
• 掩码语言模型
• pytorch license: cc-by-4.0

IceBERT-xlmr-ic3

该模型采用RoBERTa-base架构，通过fairseq框架训练而成。初始模型基于xlm-roberta-base进行微调。这是我们针对冰岛语训练的众多模型之一，更多技术细节请参阅下文引用的论文。训练数据规模如下表所示。

引用说明

本模型的技术细节详见论文https://arxiv.org/abs/2201.05601。若使用该模型，请引用该论文。

@article{DBLP:journals/corr/abs-2201-05601,
  author    = {V{\'{e}}steinn Sn{\ae}bjarnarson and
               Haukur Barri S{\'{\i}}monarson and
               P{\'{e}}tur Orri Ragnarsson and
               Svanhv{\'{\i}}t Lilja Ing{\'{o}}lfsd{\'{o}}ttir and
               Haukur P{\'{a}}ll J{\'{o}}nsson and
               Vilhj{\'{a}}lmur {\TH}orsteinsson and
               Hafsteinn Einarsson},
  title     = {优质语言模型的秘诀：预热训练与洁净爬取语料},
  journal   = {CoRR},
  volume    = {abs/2201.05601},
  year      = {2022},
  url       = {https://arxiv.org/abs/2201.05601},
  eprinttype = {arXiv},
  eprint    = {2201.05601},
  timestamp = {2022年1月20日 14:21:35 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2201-05601.bib},
  bibsource = {dblp计算机科学文献库, https://dblp.org}
}