spaCy/website/docs/api/architectures.md
2020-07-29 19:41:34 +02:00

4.8 KiB

title teaser source menu
Model Architectures Pre-defined model architectures included with the core library spacy/ml/models
Tok2Vec
tok2vec
Transformers
transformers
Parser & NER
parser
Text Classification
textcat
Entity Linking
entitylinker

TODO: intro and how architectures work, link to registry, custom models usage etc.

Tok2Vec architectures

spacy.HashEmbedCNN.v1

spacy.HashCharEmbedCNN.v1

spacy.HashCharEmbedBiLSTM.v1

Transformer architectures

The following architectures are provided by the package spacy-transformers. See the usage documentation for how to integrate the architectures into your training config.

spacy-transformers.TransformerModel.v1

Example Config

[model]
@architectures = "spacy-transformers.TransformerModel.v1"
name = "roberta-base"
tokenizer_config = {"use_fast": true}

[model.get_spans]
@span_getters = "strided_spans.v1"
window = 128
stride = 96
Name Type Description
name str Any model name that can be loaded by transformers.AutoModel.
get_spans Callable Function that takes a batch of Doc object and returns lists of Span objects to process by the transformer. See here for built-in options and examples.
tokenizer_config Dict[str, Any] Tokenizer settings passed to transformers.AutoTokenizer.

spacy-transformers.Tok2VecListener.v1

Example Config

[model]
@architectures = "spacy-transformers.Tok2VecListener.v1"
grad_factor = 1.0

[model.pooling]
@layers = "reduce_mean.v1"
Name Type Description
grad_factor float Factor for weighting the gradient if multiple components listen to the same transformer model.
pooling Model[Ragged, Floats2d] Pooling layer to determine how the vector for each spaCy token will be computed.

Parser & NER architectures

spacy.TransitionBasedParser.v1

Example Config

[model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 6
hidden_width = 64
maxout_pieces = 2

[model.tok2vec]
# ...
Name Type Description
tok2vec Model
nr_feature_tokens int
hidden_width int
maxout_pieces int
use_upper bool
nO int

Text classification architectures

spacy.TextCatEnsemble.v1

spacy.TextCatBOW.v1

spacy.TextCatCNN.v1

spacy.TextCatLowData.v1

Entity linking architectures

spacy.EntityLinker.v1