glove_train¶
This is one of the test pipelines included in Pimlico’s repository. See Module test pipelines for more details.
Config file¶
The complete config file for this test pipeline:
# Train GloVe embeddings on a tiny corpus
[pipeline]
name=glove_train
release=latest
# Take tokenized text input from a prepared Pimlico dataset
[europarl]
type=pimlico.datatypes.corpora.GroupedCorpus
data_point_type=TokenizedDocumentType
dir=%(test_data_dir)s/datasets/corpora/tokenized
[glove]
type=pimlico.modules.embeddings.glove
# Set low, since we're training on a tiny corpus
min_count=1
# TODO Set more options