transformers/model_cards/monologg/koelectra-base-generator

language
ko

KoELECTRA (Base Generator)

Pretrained ELECTRA Language Model for Korean (koelectra-base-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-generator")
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-generator")

Tokenizer example

>>> from transformers import ElectraTokenizer
>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-generator")
>>> tokenizer.tokenize("[CLS] 한국어 ELECTRA를 공유합니다. [SEP]")
['[CLS]', '한국어', 'E', '##L', '##EC', '##T', '##RA', '##를', '공유', '##합니다', '.', '[SEP]']
>>> tokenizer.convert_tokens_to_ids(['[CLS]', '한국어', 'E', '##L', '##EC', '##T', '##RA', '##를', '공유', '##합니다', '.', '[SEP]'])
[2, 18429, 41, 6240, 15229, 6204, 20894, 5689, 12622, 10690, 18, 3]

Example using ElectraForMaskedLM

from transformers import pipeline

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

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