KoELECTRA v3 (基础生成器)

针对韩文的预训练ELECTRA语言模型 (koelectra-base-v3-generator)

更多详情，请参见 original repository 。

用法

加载模型和标记器

>>> from transformers import ElectraModel, ElectraTokenizer

>>> model = ElectraModel.from_pretrained("monologg/koelectra-base-v3-generator")
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-v3-generator")

标记器示例

>>> from transformers import ElectraTokenizer
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-v3-generator")
>>> tokenizer.tokenize("[CLS] 한국어 ELECTRA를 공유합니다. [SEP]")
['[CLS]', '한국어', 'EL', '##EC', '##TRA', '##를', '공유', '##합니다', '.', '[SEP]']
>>> tokenizer.convert_tokens_to_ids(['[CLS]', '한국어', 'EL', '##EC', '##TRA', '##를', '공유', '##합니다', '.', '[SEP]'])
[2, 11229, 29173, 13352, 25541, 4110, 7824, 17788, 18, 3]

使用ElectraForMaskedLM的示例

from transformers import pipeline

fill_mask = pipeline(
    "fill-mask",
    model="monologg/koelectra-base-v3-generator",
    tokenizer="monologg/koelectra-base-v3-generator"
)

print(fill_mask("나는 {} 밥을 먹었다.".format(fill_mask.tokenizer.mask_token)))