class Config(_EncoderBaseModel.Config):
class BertModelInput(_EncoderBaseModel.Config.ModelInput):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(max_seq_len=128)
inputs: BertModelInput = BertModelInput()
encoder: TransformerSentenceEncoderBase.Config = (
HuggingFaceBertSentenceEncoder.Config()
)
class Config(_EncoderPairwiseModel.Config):
class ModelInput(_EncoderPairwiseModel.Config.ModelInput):
tokens1: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text1"], max_seq_len=128)
tokens2: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text2"], max_seq_len=128)
inputs: ModelInput = ModelInput()
encoder: TransformerSentenceEncoderBase.Config = (
HuggingFaceBertSentenceEncoder.Config())
class Config(NewBertModel.Config):
class ModelInput(BaseModel.Config.ModelInput):
squad_input: SquadForBERTTensorizer.Config = SquadForBERTTensorizer.Config(
max_seq_len=256)
# is_impossible label
has_answer: LabelTensorizer.Config = LabelTensorizer.Config(
column="has_answer")
inputs: ModelInput = ModelInput()
encoder: TransformerSentenceEncoderBase.Config = HuggingFaceBertSentenceEncoder.Config(
)
decoder: MLPDecoder.Config = MLPDecoder.Config(out_dim=2)
output_layer: SquadOutputLayer.Config = SquadOutputLayer.Config()
class Config(BasePairwiseModel.Config):
class ModelInput(ModelInputBase):
tokens1: BERTTensorizer.Config = BERTTensorizer.Config(
columns=["text1"], max_seq_len=128)
tokens2: BERTTensorizer.Config = BERTTensorizer.Config(
columns=["text2"], max_seq_len=128)
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens1", "tokens2"], indexes=[2, 2])
inputs: ModelInput = ModelInput()
encoder: TransformerSentenceEncoderBase.Config = (
HuggingFaceBertSentenceEncoder.Config())
shared_encoder: bool = True
class Config(BaseModel.Config):
class BertModelInput(BaseModel.Config.ModelInput):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(
max_seq_len=128)
dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens"], indexes=[2])
inputs: BertModelInput = BertModelInput()
encoder: TransformerSentenceEncoderBase.Config = (
HuggingFaceBertSentenceEncoder.Config())
decoder: MLPDecoder.Config = MLPDecoder.Config()
output_layer: ClassificationOutputLayer.Config = (
ClassificationOutputLayer.Config())
class Config(BasePairwiseModel.Config):
class ModelInput(ModelInputBase):
tokens1: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text1"], max_seq_len=128)
tokens2: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text2"], max_seq_len=128)
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens1", "tokens2"], indexes=[2, 2])
inputs: ModelInput = ModelInput()
encoder: TransformerSentenceEncoderBase.Config = (
HuggingFaceBertSentenceEncoder.Config())
# Decoder is a fully connected layer that expects concatenated encodings.
# So, if decoder is provided we will concatenate the encodings from the
# encoders and then pass to the decoder.
decoder: Optional[MLPDecoder.Config] = MLPDecoder.Config()
shared_encoder: bool = True