t5
allennlp_models.generation.models.t5
T5#
@Model.register("t5")
class T5(Model):
| def __init__(
| self,
| vocab: Vocabulary,
| model_name: str,
| beam_search: Lazy[BeamSearch] = Lazy(BeamSearch, beam_size=3, max_steps=50),
| checkpoint_wrapper: Optional[CheckpointWrapper] = None,
| weights_path: Optional[Union[str, PathLike]] = None,
| **kwargs
| ) -> None
tokenizer#
class T5(Model):
| ...
| @property
| def tokenizer(self) -> PretrainedTransformerTokenizer
forward#
class T5(Model):
| ...
| def forward(
| self,
| source_tokens: TextFieldTensors,
| target_tokens: Optional[TextFieldTensors] = None
| ) -> Dict[str, torch.Tensor]
Performs the forward step of T5.
Parameters¶
-
source_tokens :
TextFieldTensors
The source tokens for the encoder. We assume they are stored under thetokens
key/namespace. -
target_tokens :
TextFieldTensors
, optional (default =None
)
The target tokens for the decoder. We assume they are also stored under thetokens
key/namespace. If no target tokens are given during training / validation, the source tokens are shifted to the right by 1.
Returns¶
Dict[str, torch.Tensor]
Contains theloss
whentarget_tokens
is provided. And during prediction, includespredictions
andpredicted_log_probs
from beam search.
make_output_human_readable#
class T5(Model):
| ...
| def make_output_human_readable(
| self,
| output_dict: Dict[str, torch.Tensor]
| ) -> Dict[str, Any]
get_metrics#
class T5(Model):
| ...
| def get_metrics(self, reset: bool = False) -> Dict[str, float]
default_predictor#
class T5(Model):
| ...
| default_predictor = "seq2seq"