class Config(Tensorizer.Config):
#: The name of the slot label column to parse from the data source.
slot_column: str = "slots"
#: The name of the text column to parse from the data source.
#: We need this to be able to generate tensors which correspond to input text.
text_column: str = "text"
#: The tokenizer to use to split input text into tokens. This should be
#: configured in a way which yields tokens consistent with the tokens input to
#: or output by a model, so that the labels generated by this tensorizer
#: will match the indices of the model's tokens.
tokenizer: Tokenizer.Config = Tokenizer.Config()
#: Whether to allow for unknown labels at test/prediction time
allow_unknown: bool = False
class Config(Tensorizer.Config):
column: str = "text_seq"
max_seq_len: Optional[int] = None
#: sentence markers
add_bos_token: bool = False
add_eos_token: bool = False
use_eos_token_for_bos: bool = False
#: list markers
add_bol_token: bool = False
add_eol_token: bool = False
use_eol_token_for_bol: bool = False
#: The tokenizer to use to split input text into tokens.
tokenizer: Tokenizer.Config = Tokenizer.Config()
class Config(BERTTensorizer.Config):
vocab_file: str = "/mnt/vol/nlp_technologies/xlm/vocab_xnli_15"
tokenizer: Tokenizer.Config = Tokenizer.Config()
is_fairseq: bool = False
pretraining: bool = False
max_seq_len: Optional[int] = 256
max_vocab: int = 95000
min_count: int = 0
language_columns: List[str] = ["language"]
lang2id: Dict[str, int] = DEFAULT_LANG2ID_DICT
reset_positions: bool = False
has_language_in_data: bool = False
use_language_embeddings: bool = True
class Config(Tensorizer.Config):
#: The name of the text column to parse from the data source.
column: str = "text"
#: The tokenizer to use to split input text into tokens.
tokenizer: Tokenizer.Config = Tokenizer.Config()
#: The max token length for input text.
max_seq_len: Optional[int] = None
#: The max byte length for a token.
max_byte_len: int = 15
#: Offset to add to all non-padding bytes
offset_for_non_padding: int = 0
add_bos_token: bool = False
add_eos_token: bool = False
use_eos_token_for_bos: bool = False
class Config(BERTTensorizerBase.Config):
vocab_file: str = "/mnt/vol/nlp_technologies/xlm/vocab_xnli_15"
tokenizer: Tokenizer.Config = Tokenizer.Config()
max_vocab: int = 95000
min_count: int = 0
# language identifiers for extracting the language from a row of data
# during numberize
language_column: str = "language"
# language-to-id mapping used to obtain language embeddings
lang2id: Dict[str, int] = LANG2ID_15
# Controls whether language is being read from the data file (which
# is what happens for finetuning) or being added during processing
# (which is what happens during pretraining)
has_language_in_data: bool = False
# controls whether we train with language embeddings or not
use_language_embeddings: bool = True
class Config(Tensorizer.Config):
#: The name of the text column to parse from the data source.
column: str = "text"
#: The tokenizer to use to split input text into tokens.
tokenizer: Tokenizer.Config = Tokenizer.Config()
add_bos_token: bool = False
add_eos_token: bool = False
use_eos_token_for_bos: bool = False
max_seq_len: Optional[int] = None
#: If False, will not create token vocab during initialization. The vocab will
#: need to be set during model initialization (e.g. see WordEmbedding)
build_vocab: bool = True
vocab_file: str = ""
#: The number of lines in the above provided vocab_file to add to the
#: overall vocab
vocab_file_size_limit: int = 0
def setUp(self):
self.data_source = SquadDataSource.from_config(
SquadDataSource.Config(
train_filename=tests_module.test_file("squad_tiny.json"),
eval_filename=None,
test_filename=None,
))
self.tensorizer_with_wordpiece = SquadTensorizer.from_config(
SquadTensorizer.Config(
tokenizer=WordPieceTokenizer.Config(
wordpiece_vocab_path=
"pytext/data/test/data/wordpiece_1k.txt"),
max_seq_len=250,
))
self.tensorizer_with_alphanumeric = SquadTensorizer.from_config(
SquadTensorizer.Config(
tokenizer=Tokenizer.Config(split_regex=r"\W+"),
max_seq_len=250))
class Config(Tensorizer.Config):
text_column: str = "text"
dict_column: str = "dict"
#: tokenizer to split text and create dict tensors of the same size.
tokenizer: Tokenizer.Config = Tokenizer.Config()
class Config(Tensorizer.Config):
# BERT style models support multiple text inputs
columns: List[str] = ["text"]
tokenizer: Tokenizer.Config = Tokenizer.Config()
vocab_file: str = ""
max_seq_len: int = 256
