KoELECTRA v2 (Base Generator)
Pretrained ELECTRA Language Model for Korean (koelectra-base-v2-generator
)
For more detail, please see original repository.
Usage
Load model and tokenizer
>>> from transformers import ElectraModel, ElectraTokenizer
>>> model = ElectraModel.from_pretrained("monologg/koelectra-base-v2-generator")
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-v2-generator")
Tokenizer example
>>> from transformers import ElectraTokenizer
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-v2-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, 5084, 16248, 3770, 19059, 29965, 2259, 10431, 5, 3]
Example using ElectraForMaskedLM
from transformers import pipeline
fill_mask = pipeline(
"fill-mask",
model="monologg/koelectra-base-v2-generator",
tokenizer="monologg/koelectra-base-v2-generator"
)
print(fill_mask("나는 {} 밥을 먹었다.".format(fill_mask.tokenizer.mask_token)))