模型:
AdapterHub/bert-base-uncased-pf-emotion
这是一个对bert-base-uncased模型的适配器,该模型是在 emotion 数据集上训练的,并包含用于分类的预测头。
此适配器适用于 adapter-transformers 库的使用。
首先,安装adapter-transformers:
pip install -U adapter-transformers
注意:adapter-transformers是transformers的一个分支,它在具有适配器支持的情况下作为可插拔替代品。 More
现在,可以像这样加载和激活适配器:
from transformers import AutoModelWithHeads model = AutoModelWithHeads.from_pretrained("bert-base-uncased") adapter_name = model.load_adapter("AdapterHub/bert-base-uncased-pf-emotion", source="hf") model.active_adapters = adapter_name
此适配器的训练代码可在 https://github.com/adapter-hub/efficient-task-transfer 处找到。特别是,所有任务的训练配置可以在 here 处找到。
更多结果信息请参阅 the paper 。
如果您使用此适配器,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", }