适用于 roberta-base 的适配器 AdapterHub/roberta-base-pf-boolq 的 ONNX 导出版本

将 AdapterHub/roberta-base-pf-boolq 转换为 UKP SQuARE 格式

使用方法

onnx_path = hf_hub_download(repo_id='UKP-SQuARE/roberta-base-pf-boolq-onnx', filename='model.onnx') # 或使用 model_quant.onnx 进行量化
onnx_model = InferenceSession(onnx_path, providers=['CPUExecutionProvider'])

context = 'English orthography typically represents vowel sounds with the five conventional vowel letters ⟨a, e, i, o, u⟩, as well as ⟨y⟩, which may also be a consonant depending on context. However, outside of abbreviations, there are a handful of words in English that do not have vowels, either because the vowel sounds are not written with vowel letters or because the words themselves are pronounced without vowel sounds'.
question = 'can there be a word without a vowel'
tokenizer = AutoTokenizer.from_pretrained('UKP-SQuARE/roberta-base-pf-boolq-onnx')

inputs = tokenizer(question, context, padding=True, truncation=True, return_tensors='np')
inputs = {key: np.array(inputs[key], dtype=np.int64) for key in inputs}
outputs = onnx_model.run(input_feed=dict(inputs), output_names=None)

架构与训练

该适配器的训练代码可在 https://github.com/adapter-hub/efficient-task-transfer 获取。 所有任务的训练配置可在此处找到。

评估结果

有关结果的更多信息，请参阅论文。

引用

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\",
}