模型:
AdapterHub/roberta-base-pf-hotpotqa
这是一个针对roberta-base模型的适配器,通过训练 hotpot_qa 数据集并包含了一个用于问答的预测头部。
此适配器适用于 adapter-transformers 库。
首先,安装adapter-transformers:
pip install -U adapter-transformers
注意:adapter-transformers是transformers的一个分支,它可以作为带有适配器支持的替代品。
现在,可以像这样加载和激活适配器:
from transformers import AutoModelWithHeads model = AutoModelWithHeads.from_pretrained("roberta-base") adapter_name = model.load_adapter("AdapterHub/roberta-base-pf-hotpotqa", 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可以在 here 中找到。
有关结果的更多信息,请参考 the paper 。
如果您使用了这个适配器,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", }