模型:

AdapterHub/roberta-base-pf-hotpotqa

英文

适配器 AdapterHub/roberta-base-pf-hotpotqa 适用于roberta-base

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。

用法

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

架构与训练

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。

评估结果

有关结果的更多信息,请参考 the paper

引用

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",
}