keras-xlnet 0.13.0

XLNet implemented in Keras

Keras XLNet

[中文|English]

Unofficial implementation of XLNet.

Install

pip install keras-xlnet

Usage

Load Pretrained Checkpoints

import os
from keras_xlnet import Tokenizer, load_trained_model_from_checkpoint

checkpoint_path = '.../xlnet_cased_L-24_H-1024_A-16'

tokenizer = Tokenizer(os.path.join(checkpoint_path, 'spiece.model'))
model = load_trained_model_from_checkpoint(
    config_path=os.path.join(checkpoint_path, 'xlnet_config.json'),
    checkpoint_path=os.path.join(checkpoint_path, 'xlnet_model.ckpt'),
    batch_size=16,
    memory_len=512,
    target_len=128,
    in_train_phase=False,
)
model.summary()

Arguments batch_size, memory_len and target_len are maximum sizes used for initialization of memories. The model used for training a language model is returned if in_train_phase is True, otherwise a model used for fine-tuning will be returned.

About I/O

in_train_phase is False

3 inputs:

• IDs of tokens, with shape (batch_size, target_len).
• IDs of segments, with shape (batch_size, target_len).
• Length of memories, with shape (batch_size, 1).

1 output:

• The feature for each token, with shape (batch_size, target_len, units).

in_train_phase is True

4 inputs:

• IDs of tokens, with shape (batch_size, target_len).
• IDs of segments, with shape (batch_size, target_len).
• Length of memories, with shape (batch_size, 1).
• Masks of tokens, with shape (batch_size, target_len).

1 output:

• The probability of each token in each position, with shape (batch_size, target_len, num_token).