KoELECTRA v2（基础鉴别器）

针对韩文的预训练 ELECTRA 语言模型（koelectra-base-v2-discriminator）

更多详细信息，请参见 original repository 。

用法

加载模型和分词器

>>> from transformers import ElectraModel, ElectraTokenizer

>>> model = ElectraModel.from_pretrained("monologg/koelectra-base-v2-discriminator")
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-v2-discriminator")

分词器示例

>>> from transformers import ElectraTokenizer
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-v2-discriminator")
>>> 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, 5084, 16248, 3770, 19059, 29965, 2259, 10431, 5, 3]

使用 ElectraForPreTraining 进行示例

import torch
from transformers import ElectraForPreTraining, ElectraTokenizer

discriminator = ElectraForPreTraining.from_pretrained("monologg/koelectra-base-v2-discriminator")
tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-v2-discriminator")

sentence = "나는 방금 밥을 먹었다."
fake_sentence = "나는 내일 밥을 먹었다."

fake_tokens = tokenizer.tokenize(fake_sentence)
fake_inputs = tokenizer.encode(fake_sentence, return_tensors="pt")

discriminator_outputs = discriminator(fake_inputs)
predictions = torch.round((torch.sign(discriminator_outputs[0]) + 1) / 2)

print(list(zip(fake_tokens, predictions.tolist()[1:-1])))