predefined_args = {
        'attention_cell': 'multi_head',
        'num_layers': 12,
        'units': 768,
        'hidden_size': 3072,
        'max_length': 512,
        'num_heads': 12,
        'scaled': True,
        'dropout': 0.1,
        'use_residual': True,
        'embed_size': 768,
        'embed_dropout': 0.1,
        'token_type_vocab_size': 2,
        'word_embed': None,
    }

>>> import torch
>>> from kobert import get_pytorch_kobert_model
>>> input_ids = torch.LongTensor([[31, 51, 99], [15, 5, 0]])
>>> input_mask = torch.LongTensor([[1, 1, 1], [1, 1, 0]])
>>> token_type_ids = torch.LongTensor([[0, 0, 1], [0, 1, 0]])
>>> model, vocab  = get_pytorch_kobert_model()
>>> sequence_output, pooled_output = model(input_ids, input_mask, token_type_ids)
>>> pooled_output.shape
torch.Size([2, 768])
>>> vocab
Vocab(size=8002, unk="[UNK]", reserved="['[MASK]', '[SEP]', '[CLS]']")
>>> # Last Encoding Layer
>>> sequence_output[0]
tensor([[-0.2461,  0.2428,  0.2590,  ..., -0.4861, -0.0731,  0.0756],
        [-0.2478,  0.2420,  0.2552,  ..., -0.4877, -0.0727,  0.0754],
        [-0.2472,  0.2420,  0.2561,  ..., -0.4874, -0.0733,  0.0765]],
       grad_fn=<SelectBackward>)

>>> import onnxruntime
>>> import numpy as np
>>> from kobert import get_onnx_kobert_model
>>> onnx_path = get_onnx_kobert_model()
>>> sess = onnxruntime.InferenceSession(onnx_path)
>>> input_ids = [[31, 51, 99], [15, 5, 0]]
>>> input_mask = [[1, 1, 1], [1, 1, 0]]
>>> token_type_ids = [[0, 0, 1], [0, 1, 0]]
>>> len_seq = len(input_ids[0])
>>> pred_onnx = sess.run(None, {'input_ids':np.array(input_ids),
>>>                             'token_type_ids':np.array(token_type_ids),
>>>                             'input_mask':np.array(input_mask),
>>>                             'position_ids':np.array(range(len_seq))})
>>> # Last Encoding Layer
>>> pred_onnx[-2][0]
array([[-0.24610452,  0.24282141,  0.25895312, ..., -0.48613444,
        -0.07305173,  0.07560554],
       [-0.24783179,  0.24200465,  0.25520486, ..., -0.4877185 ,
        -0.0727044 ,  0.07536091],
       [-0.24721591,  0.24196623,  0.2560626 , ..., -0.48743123,
        -0.07326943,  0.07650235]], dtype=float32)

>>> import mxnet as mx
>>> from kobert import get_mxnet_kobert_model
>>> input_id = mx.nd.array([[31, 51, 99], [15, 5, 0]])
>>> input_mask = mx.nd.array([[1, 1, 1], [1, 1, 0]])
>>> token_type_ids = mx.nd.array([[0, 0, 1], [0, 1, 0]])
>>> model, vocab = get_mxnet_kobert_model(use_decoder=False, use_classifier=False)
>>> encoder_layer, pooled_output = model(input_id, token_type_ids)
>>> pooled_output.shape
(2, 768)
>>> vocab
Vocab(size=8002, unk="[UNK]", reserved="['[MASK]', '[SEP]', '[CLS]']")
>>> # Last Encoding Layer
>>> encoder_layer[0]
[[-0.24610372  0.24282135  0.2589539  ... -0.48613444 -0.07305248
   0.07560539]
 [-0.24783105  0.242005    0.25520545 ... -0.48771808 -0.07270523
   0.07536077]
 [-0.24721491  0.241966    0.25606337 ... -0.48743105 -0.07327032
   0.07650219]]
<NDArray 3x768 @cpu(0)>

>>> from gluonnlp.data import SentencepieceTokenizer
>>> from kobert import get_tokenizer
>>> tok_path = get_tokenizer()
>>> sp  = SentencepieceTokenizer(tok_path)
>>> sp('한국어 모델을 공유합니다.')
['▁한국', '어', '▁모델', '을', '▁공유', '합니다', '.']