class Config(BaseModel.Config):
class ModelInput(Model.Config.ModelInput):
tokens: TokenTensorizer.Config = TokenTensorizer.Config(
add_bos_token=True, add_eos_token=True)
inputs: ModelInput = ModelInput()
embedding: WordEmbedding.Config = WordEmbedding.Config()
representation: BiLSTM.Config = BiLSTM.Config(bidirectional=False)
decoder: Optional[MLPDecoder.Config] = MLPDecoder.Config()
output_layer: LMOutputLayer.Config = LMOutputLayer.Config()
tied_weights: bool = False
stateful: bool = False
class Config(BaseModel.Config):
class ModelInput(Model.Config.ModelInput):
tokens: Optional[TokenTensorizer.Config] = TokenTensorizer.Config(
add_bos_token=True, add_eos_token=True)
inputs: ModelInput = ModelInput()
embedding: WordEmbedding.Config = WordEmbedding.Config()
representation: Union[BiLSTM.Config,
CNN.Config] = BiLSTM.Config(bidirectional=False)
decoder: Optional[MLPDecoder.Config] = MLPDecoder.Config()
output_layer: LMOutputLayer.Config = LMOutputLayer.Config()
tied_weights: bool = False
stateful: bool = False
caffe2_format: ExporterType = ExporterType.PREDICTOR
class Config(BaseModel.Config):
class InputConfig(ConfigBase):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(max_seq_len=128)
inputs: InputConfig = InputConfig()
encoder: TransformerSentenceEncoderBase.Config = TransformerSentenceEncoder.Config()
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: LMOutputLayer.Config = LMOutputLayer.Config()
mask_prob: float = 0.15
mask_bos: bool = False
# masking
masking_strategy: MaskingStrategy = MaskingStrategy.RANDOM
# tie weights determines whether the input embedding weights are used
# in the output vocabulary projection as well
tie_weights: bool = True
class Config(ConfigBase):
"""
Configuration class for `LMLSTM`.
Attributes:
representation (BiLSTM.Config): Config for the BiLSTM representation.
decoder (MLPDecoder.Config): Config for the MLP Decoder.
output_layer (LMOutputLayer.Config): Config for the language model
output layer.
tied_weights (bool): If `True` use a common weights matrix between
the word embeddings and the decoder. Defaults to `False`.
stateful (bool): If `True`, do not reset hidden state of LSTM
across batches.
"""
representation: BiLSTM.Config = BiLSTM.Config(bidirectional=False)
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: LMOutputLayer.Config = LMOutputLayer.Config()
tied_weights: bool = False
stateful: bool = False