Sha256: fadbec4eca9446b3cf366a1654c31a2f4b60613f11f510faacd17d5cd0a4ed8b
Contents?: true
Size: 1.69 KB
Versions: 21
Compression:
Stored size: 1.69 KB
Contents
# This is an auto-generated partial config. To use it with 'spacy train'
# you can run spacy init fill-config to auto-fill all default settings:
# python -m spacy init fill-config ./base_config.cfg ./config.cfg
[paths]
train = null
dev = null
[system]
gpu_allocator = null
[nlp]
lang = "en"
pipeline = ["tok2vec","textcat"]
batch_size = 1000
[components]
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.tok2vec.model.encode.width}
attrs = ["ORTH", "SHAPE"]
rows = [5000, 2500]
include_static_vectors = true
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
depth = 8
window_size = 1
maxout_pieces = 3
[components.textcat]
factory = "textcat"
[components.textcat.model]
@architectures = "spacy.TextCatEnsemble.v2"
nO = null
[components.textcat.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
[components.textcat.model.linear_model]
@architectures = "spacy.TextCatBOW.v1"
exclusive_classes = true
ngram_size = 1
no_output_layer = false
[corpora]
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 2000
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
[training.optimizer]
@optimizers = "Adam.v1"
[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
[initialize]
vectors = "en_core_web_lg"
Version data entries
21 entries across 21 versions & 1 rubygems