模型:
AdapterHub/bert-base-uncased-pf-mrpc
适用于 bert-large-uncased 模型的适配器,该模型在数据集上进行了训练,并包含了用于分类的预测头。
该适配器是为了与 adapter-transformers 库一起使用而创建的。
首先,安装 adapter-transformers :
pip install -U adapter-transformers
注意:adapter-transformers 是 transformers 的一个分支,具有适配器支持,可以作为其替代品。 More
现在,可以按如下方式加载和激活适配器:
from transformers import AutoModelWithHeads model = AutoModelWithHeads.from_pretrained("bert-base-uncased") adapter_name = model.load_adapter("AdapterHub/bert-base-uncased-pf-mrpc", source="hf") model.active_adapters = adapter_name
该适配器的训练代码可在 https://github.com/adapter-hub/efficient-task-transfer 找到。特别是,所有任务的训练配置都可以在其中找到 here 。
更多结果信息请参阅 the paper 。
如果您使用了该适配器,请引用我们的论文 "What to Pre-Train on? Efficient Intermediate Task Selection" :
@inproceedings{poth-etal-2021-pre, title = "{W}hat to Pre-Train on? {E}fficient Intermediate Task Selection", author = {Poth, Clifton and Pfeiffer, Jonas and R{"u}ckl{'e}, Andreas and Gurevych, Iryna}, booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2021", address = "Online and Punta Cana, Dominican Republic", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.emnlp-main.827", pages = "10585--10605", }