标签:

• bert
• oBERT 语言: 英文 数据集: squad

bert-large-uncased-finetuned-squadv1

该模型是基于SQuADv1任务对bert-large-uncased模型进行微调的版本。

它是论文《最优BERT外科医生：面向大语言模型的可扩展且精确的二阶剪枝方法》(The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models)研究工作的成果之一。

SQuADv1开发集表现：

精确匹配率(EM) = 84.46
F1分数 = 91.23

代码仓库：https://github.com/neuralmagic/sparseml/tree/main/research/optimal_BERT_surgeon_oBERT

若您认为本模型有帮助，请考虑引用我们的研究成果。

引用信息

@article{kurtic2022optimal,
  title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
  author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
  journal={arXiv preprint arXiv:2203.07259},
  year={2022}
}