tfm.nlp.encoders.ReuseEncoderConfig

Reuse encoder configuration.

Inherits From: Config, ParamsDict

tfm.nlp.encoders.ReuseEncoderConfig(
    default_params: dataclasses.InitVar[Optional[Mapping[str, Any]]] = None,
    restrictions: dataclasses.InitVar[Optional[List[str]]] = None,
    vocab_size: int = 30522,
    hidden_size: int = 768,
    num_layers: int = 12,
    num_attention_heads: int = 12,
    hidden_activation: str = 'gelu',
    intermediate_size: int = 3072,
    dropout_rate: float = 0.1,
    attention_dropout_rate: float = 0.1,
    max_position_embeddings: int = 512,
    type_vocab_size: int = 2,
    initializer_range: float = 0.02,
    embedding_size: Optional[int] = None,
    output_range: Optional[int] = None,
    return_all_encoder_outputs: bool = False,
    norm_first: bool = False,
    reuse_attention: int = -1,
    use_relative_pe: bool = False,
    pe_max_seq_length: int = 512,
    max_reuse_layer_idx: int = 6
)

BUILDER

default_params Dataclass field restrictions Dataclass field vocab_size Dataclass field hidden_size Dataclass field num_layers Dataclass field num_attention_heads Dataclass field hidden_activation Dataclass field intermediate_size Dataclass field dropout_rate Dataclass field attention_dropout_rate Dataclass field max_position_embeddings Dataclass field type_vocab_size Dataclass field initializer_range Dataclass field embedding_size Dataclass field output_range Dataclass field return_all_encoder_outputs Dataclass field norm_first Dataclass field reuse_attention Dataclass field use_relative_pe Dataclass field pe_max_seq_length Dataclass field max_reuse_layer_idx Dataclass field

Methods

as_dict

View source

as_dict()

Returns a dict representation of params_dict.ParamsDict.

For the nested params_dict.ParamsDict, a nested dict will be returned.

from_args

View source

@classmethod
from_args(
    *args, **kwargs
)

Builds a config from the given list of arguments.

from_json

View source

@classmethod
from_json(
    file_path: str
)

Wrapper for from_yaml.

from_yaml

View source

@classmethod
from_yaml(
    file_path: str
)

get

View source

get(
    key, value=None
)

Accesses through built-in dictionary get method.

lock

View source

lock()

Makes the ParamsDict immutable.

override

View source

override(
    override_params, is_strict=True
)

Override the ParamsDict with a set of given params.

Args

override_params a dict or a ParamsDict specifying the parameters to be overridden. is_strict a boolean specifying whether override is strict or not. If True, keys in override_params must be present in the ParamsDict. If False, keys in override_params can be different from what is currently defined in the ParamsDict. In this case, the ParamsDict will be extended to include the new keys.

replace

View source

replace(
    **kwargs
)

Overrides/returns a unlocked copy with the current config unchanged.

validate

View source

validate()

Validate the parameters consistency based on the restrictions.

This method validates the internal consistency using the pre-defined list of restrictions. A restriction is defined as a string which specifies a binary operation. The supported binary operations are {'==', '!=', '<', '<=', '>', '>='}. Note that the meaning of these operators are consistent with the underlying Python immplementation. Users should make sure the define restrictions on their type make sense.

For example, for a ParamsDict like the following

a:
  a1: 1
  a2: 2
b:
  bb:
    bb1: 10
    bb2: 20
  ccc:
    a1: 1
    a3: 3

one can define two restrictions like this ['a.a1 == b.ccc.a1', 'a.a2 <= b.bb.bb2']

What it enforces are

  • a.a1 = 1 == b.ccc.a1 = 1
  • a.a2 = 2 <= b.bb.bb2 = 20

Raises

KeyError if any of the following happens (1) any of parameters in any of restrictions is not defined in ParamsDict, (2) any inconsistency violating the restriction is found. ValueError if the restriction defined in the string is not supported.

__contains__

View source

__contains__(
    key
)

Implements the membership test operator.

__eq__

__eq__(
    other
)

IMMUTABLE_TYPES (<class 'str'>, <class 'int'>, <class 'float'>, <class 'bool'>, <class 'NoneType'>) RESERVED_ATTR ['_locked', '_restrictions'] SEQUENCE_TYPES (<class 'list'>, <class 'tuple'>) attention_dropout_rate 0.1 default_params None dropout_rate 0.1 embedding_size None hidden_activation 'gelu' hidden_size 768 initializer_range 0.02 intermediate_size 3072 max_position_embeddings 512 max_reuse_layer_idx 6 norm_first False num_attention_heads 12 num_layers 12 output_range None pe_max_seq_length 512 restrictions None return_all_encoder_outputs False reuse_attention -1 type_vocab_size 2 use_relative_pe False vocab_size 30522