From 8a86a35eab45a69d795c2950da61058047d1a516 Mon Sep 17 00:00:00 2001 From: Adriane Boyd Date: Fri, 9 Sep 2022 15:10:04 +0200 Subject: [PATCH] Remove has_letters in config template (#11465) Due to problems with the javascript conversion in the website quickstart, remove the `has_letters` setting to simplify generating `attrs` for the default `tok2vec`. Additionally reduce `PREFIX` as in the trained pipelines. --- spacy/cli/templates/quickstart_training.jinja | 7 +------ .../cli/templates/quickstart_training_recommendations.yml | 1 - 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/spacy/cli/templates/quickstart_training.jinja b/spacy/cli/templates/quickstart_training.jinja index ae11dcafc..58864883a 100644 --- a/spacy/cli/templates/quickstart_training.jinja +++ b/spacy/cli/templates/quickstart_training.jinja @@ -271,13 +271,8 @@ factory = "tok2vec" [components.tok2vec.model.embed] @architectures = "spacy.MultiHashEmbed.v2" width = ${components.tok2vec.model.encode.width} -{% if has_letters -%} attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"] -rows = [5000, 2500, 2500, 2500] -{% else -%} -attrs = ["ORTH", "SHAPE"] -rows = [5000, 2500] -{% endif -%} +rows = [5000, 1000, 2500, 2500] include_static_vectors = {{ "true" if optimize == "accuracy" else "false" }} [components.tok2vec.model.encode] diff --git a/spacy/cli/templates/quickstart_training_recommendations.yml b/spacy/cli/templates/quickstart_training_recommendations.yml index a7bf9b74a..27945e27a 100644 --- a/spacy/cli/templates/quickstart_training_recommendations.yml +++ b/spacy/cli/templates/quickstart_training_recommendations.yml @@ -271,4 +271,3 @@ zh: accuracy: name: bert-base-chinese size_factor: 3 - has_letters: false