diff --git a/.github/contributors/jmargeta.md b/.github/contributors/jmargeta.md
new file mode 100644
index 000000000..ab13424f8
--- /dev/null
+++ b/.github/contributors/jmargeta.md
@@ -0,0 +1,106 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI GmbH](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+ * you hereby assign to us joint ownership, and to the extent that such
+ assignment is or becomes invalid, ineffective or unenforceable, you hereby
+ grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+ royalty-free, unrestricted license to exercise all rights under those
+ copyrights. This includes, at our option, the right to sublicense these same
+ rights to third parties through multiple levels of sublicensees or other
+ licensing arrangements;
+
+ * you agree that each of us can do all things in relation to your
+ contribution as if each of us were the sole owners, and if one of us makes
+ a derivative work of your contribution, the one who makes the derivative
+ work (or has it made will be the sole owner of that derivative work;
+
+ * you agree that you will not assert any moral rights in your contribution
+ against us, our licensees or transferees;
+
+ * you agree that we may register a copyright in your contribution and
+ exercise all ownership rights associated with it; and
+
+ * you agree that neither of us has any duty to consult with, obtain the
+ consent of, pay or render an accounting to the other for any use or
+ distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+ * make, have made, use, sell, offer to sell, import, and otherwise transfer
+ your contribution in whole or in part, alone or in combination with or
+ included in any product, work or materials arising out of the project to
+ which your contribution was submitted, and
+
+ * at our option, to sublicense these same rights to third parties through
+ multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+ * Each contribution that you submit is and shall be an original work of
+ authorship and you can legally grant the rights set out in this SCA;
+
+ * to the best of your knowledge, each contribution will not violate any
+ third party's copyrights, trademarks, patents, or other intellectual
+ property rights; and
+
+ * each contribution shall be in compliance with U.S. export control laws and
+ other applicable export and import laws. You agree to notify us if you
+ become aware of any circumstance which would make any of the foregoing
+ representations inaccurate in any respect. We may publicly disclose your
+ participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+ * [x] I am signing on behalf of myself as an individual and no other person
+ or entity, including my employer, has or will have rights with respect to my
+ contributions.
+
+ * [ ] I am signing on behalf of my employer or a legal entity and I have the
+ actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field | Entry |
+|------------------------------- | -------------------- |
+| Name | Jan Margeta |
+| Company name (if applicable) | KardioMe |
+| Title or role (if applicable) | Founder |
+| Date | 2020-10-16 |
+| GitHub username | jmargeta |
+| Website (optional) | kardio.me |
diff --git a/netlify.toml b/netlify.toml
index 3c17b876c..e860e4bf4 100644
--- a/netlify.toml
+++ b/netlify.toml
@@ -58,5 +58,7 @@ redirects = [
{from = "/universe", to = "/universe/project/:id", query = {id = ":id"}, force = true},
{from = "/universe", to = "/universe/category/:category", query = {category = ":category"}, force = true},
# Renamed universe projects
- {from = "/universe/project/spacy-pytorch-transformers", to = "/universe/project/spacy-transformers", force = true}
+ {from = "/universe/project/spacy-pytorch-transformers", to = "/universe/project/spacy-transformers", force = true},
+ # Old model pages
+ {from = "/models/en-starters", to = "/models/en", force = true},
]
diff --git a/spacy/cli/templates/quickstart_training_recommendations.yml b/spacy/cli/templates/quickstart_training_recommendations.yml
index 54aec2e31..47b3abbf6 100644
--- a/spacy/cli/templates/quickstart_training_recommendations.yml
+++ b/spacy/cli/templates/quickstart_training_recommendations.yml
@@ -1,17 +1,20 @@
# Recommended settings and available resources for each language, if available.
# Not all languages have recommended word vectors or transformers and for some,
# the recommended transformer for efficiency and accuracy may be the same.
-en:
- word_vectors: en_vectors_web_lg
+ar:
+ word_vectors: null
transformer:
efficiency:
- name: roberta-base
+ name: asafaya/bert-base-arabic
size_factor: 3
accuracy:
- name: roberta-base
+ name: asafaya/bert-base-arabic
size_factor: 3
+da:
+ word_vectors: da_core_news_lg
+ transformer: null
de:
- word_vectors: null
+ word_vectors: de_core_news_lg
transformer:
efficiency:
name: bert-base-german-cased
@@ -19,17 +22,26 @@ de:
accuracy:
name: bert-base-german-cased
size_factor: 3
-fr:
- word_vectors: null
+el:
+ word_vectors: el_core_news_lg
transformer:
efficiency:
- name: camembert-base
+ name: nlpaueb/bert-base-greek-uncased-v1
size_factor: 3
accuracy:
- name: camembert-base
+ name: nlpaueb/bert-base-greek-uncased-v1
+ size_factor: 3
+en:
+ word_vectors: en_core_web_lg
+ transformer:
+ efficiency:
+ name: roberta-base
+ size_factor: 3
+ accuracy:
+ name: roberta-base
size_factor: 3
es:
- word_vectors: null
+ word_vectors: es_core_news_lg
transformer:
efficiency:
name: dccuchile/bert-base-spanish-wwm-cased
@@ -37,15 +49,6 @@ es:
accuracy:
name: dccuchile/bert-base-spanish-wwm-cased
size_factor: 3
-sv:
- word_vectors: null
- transformer:
- efficiency:
- name: KB/bert-base-swedish-cased
- size_factor: 3
- accuracy:
- name: KB/bert-base-swedish-cased
- size_factor: 3
fi:
word_vectors: null
transformer:
@@ -55,14 +58,65 @@ fi:
accuracy:
name: TurkuNLP/bert-base-finnish-cased-v1
size_factor: 3
-el:
+fr:
+ word_vectors: fr_core_news_lg
+ transformer:
+ efficiency:
+ name: camembert-base
+ size_factor: 3
+ accuracy:
+ name: camembert-base
+ size_factor: 3
+it:
+ word_vectors: it_core_news_lg
+ transformers: null
+ja:
+ word_vectors: ja_core_news_lg
+ transformers: null
+lt:
+ word_vectors: lt_core_news_lg
+ transformers: null
+nb:
+ word_vectors: nb_core_news_lg
+ transformers: null
+nl:
+ word_vectors: nl_core_news_lg
+ transformer:
+ efficiency:
+ name: pdelobelle/robbert-v2-dutch-base
+ size_factor: 3
+ accuracy:
+ name: pdelobelle/robbert-v2-dutch-base
+ size_factor: 3
+pl:
+ word_vectors: pl_core_news_lg
+ transformer:
+ efficiency:
+ name: dkleczek/bert-base-polish-cased-v1
+ size_factor: 3
+ accuracy:
+ name: dkleczek/bert-base-polish-cased-v1
+ size_factor: 3
+pt:
+ word_vectors: pt_core_news_lg
+ transformer:
+ efficiency:
+ name: neuralmind/bert-base-portuguese-cased
+ size_factor: 3
+ accuracy:
+ name: neuralmind/bert-base-portuguese-cased
+ size_factor: 3
+ro:
+ word_vectors: ro_core_news_lg
+ transformers: null
+sv:
word_vectors: null
transformer:
efficiency:
- name: nlpaueb/bert-base-greek-uncased-v1
+ name: KB/bert-base-swedish-cased
size_factor: 3
accuracy:
- name: nlpaueb/bert-base-greek-uncased-v1
+ name: KB/bert-base-swedish-cased
size_factor: 3
tr:
word_vectors: null
@@ -74,7 +128,7 @@ tr:
name: dbmdz/bert-base-turkish-cased
size_factor: 3
zh:
- word_vectors: null
+ word_vectors: zh_core_web_lg
transformer:
efficiency:
name: bert-base-chinese
@@ -83,39 +137,3 @@ zh:
name: bert-base-chinese
size_factor: 3
has_letters: false
-ar:
- word_vectors: null
- transformer:
- efficiency:
- name: asafaya/bert-base-arabic
- size_factor: 3
- accuracy:
- name: asafaya/bert-base-arabic
- size_factor: 3
-pl:
- word_vectors: null
- transformer:
- efficiency:
- name: dkleczek/bert-base-polish-cased-v1
- size_factor: 3
- accuracy:
- name: dkleczek/bert-base-polish-cased-v1
- size_factor: 3
-nl:
- word_vectors: null
- transformer:
- efficiency:
- name: pdelobelle/robbert-v2-dutch-base
- size_factor: 3
- accuracy:
- name: pdelobelle/robbert-v2-dutch-base
- size_factor: 3
-pt:
- word_vectors: null
- transformer:
- efficiency:
- name: neuralmind/bert-base-portuguese-cased
- size_factor: 3
- accuracy:
- name: neuralmind/bert-base-portuguese-cased
- size_factor: 3
diff --git a/spacy/schemas.py b/spacy/schemas.py
index f3664acff..9480596f0 100644
--- a/spacy/schemas.py
+++ b/spacy/schemas.py
@@ -257,7 +257,7 @@ class TokenPattern(BaseModel):
class TokenPatternSchema(BaseModel):
- pattern: List[TokenPattern] = Field(..., minItems=1)
+ pattern: List[TokenPattern] = Field(..., min_items=1)
class Config:
extra = "forbid"
diff --git a/spacy/tests/regression/test_issue6258.py b/spacy/tests/regression/test_issue6258.py
new file mode 100644
index 000000000..03b0b9373
--- /dev/null
+++ b/spacy/tests/regression/test_issue6258.py
@@ -0,0 +1,14 @@
+import pydantic
+import pytest
+from pydantic import ValidationError
+from spacy.schemas import TokenPattern, TokenPatternSchema
+
+
+def test_issue6258():
+ """Test that the non-empty constraint pattern field is respected"""
+ # These one is valid
+ TokenPatternSchema(pattern=[TokenPattern()])
+ # But an empty pattern list should fail to validate
+ # based on the schema's constraint
+ with pytest.raises(ValidationError):
+ TokenPatternSchema(pattern=[])
diff --git a/website/docs/usage/101/_vectors-similarity.md b/website/docs/usage/101/_vectors-similarity.md
index cf5b70af2..2a8733f41 100644
--- a/website/docs/usage/101/_vectors-similarity.md
+++ b/website/docs/usage/101/_vectors-similarity.md
@@ -68,8 +68,8 @@ representation consists of 300 dimensions of `0`, which means it's practically
nonexistent. If your application will benefit from a **large vocabulary** with
more vectors, you should consider using one of the larger pipeline packages or
loading in a full vector package, for example,
-[`en_vectors_web_lg`](/models/en-starters#en_vectors_web_lg), which includes
-over **1 million unique vectors**.
+[`en_core_web_lg`](/models/en#en_core_web_lg), which includes **685k unique
+vectors**.
spaCy is able to compare two objects, and make a prediction of **how similar
they are**. Predicting similarity is useful for building recommendation systems
diff --git a/website/docs/usage/linguistic-features.md b/website/docs/usage/linguistic-features.md
index 4077cf293..af07a438f 100644
--- a/website/docs/usage/linguistic-features.md
+++ b/website/docs/usage/linguistic-features.md
@@ -1859,9 +1859,8 @@ pruning the vectors will be taken care of automatically if you set the `--prune`
flag. You can also do it manually in the following steps:
1. Start with a **word vectors package** that covers a huge vocabulary. For
- instance, the [`en_vectors_web_lg`](/models/en-starters#en_vectors_web_lg)
- starter provides 300-dimensional GloVe vectors for over 1 million terms of
- English.
+ instance, the [`en_core_web_lg`](/models/en#en_core_web_lg) package provides
+ 300-dimensional GloVe vectors for 685k terms of English.
2. If your vocabulary has values set for the `Lexeme.prob` attribute, the
lexemes will be sorted by descending probability to determine which vectors
to prune. Otherwise, lexemes will be sorted by their order in the `Vocab`.
@@ -1869,7 +1868,7 @@ flag. You can also do it manually in the following steps:
vectors you want to keep.
```python
-nlp = spacy.load('en_vectors_web_lg')
+nlp = spacy.load("en_core_web_lg")
n_vectors = 105000 # number of vectors to keep
removed_words = nlp.vocab.prune_vectors(n_vectors)
diff --git a/website/docs/usage/v2-1.md b/website/docs/usage/v2-1.md
index 4a8ef5a37..8d310f1a4 100644
--- a/website/docs/usage/v2-1.md
+++ b/website/docs/usage/v2-1.md
@@ -22,7 +22,7 @@ For more details and a behind-the-scenes look at the new release,
>
> ```bash
> $ python -m spacy pretrain ./raw_text.jsonl
-> en_vectors_web_lg ./pretrained-model
+> en_core_web_lg ./pretrained-model
> ```
spaCy v2.1 introduces a new CLI command, `spacy pretrain`, that can make your
diff --git a/website/gatsby-node.js b/website/gatsby-node.js
index 56a65aeae..b5d8c22c3 100644
--- a/website/gatsby-node.js
+++ b/website/gatsby-node.js
@@ -226,8 +226,6 @@ exports.createPages = ({ graphql, actions }) => {
const langs = result.data.site.siteMetadata.languages
const modelLangs = langs.filter(({ models }) => models && models.length)
- const starterLangs = langs.filter(({ starters }) => starters && starters.length)
-
modelLangs.forEach(({ code, name, models, example, has_examples }, i) => {
const slug = `/models/${code}`
const next = i < modelLangs.length - 1 ? modelLangs[i + 1] : null
@@ -247,28 +245,6 @@ exports.createPages = ({ graphql, actions }) => {
},
})
})
-
- starterLangs.forEach(({ code, name, starters }, i) => {
- const slug = `/models/${code}-starters`
- const next = i < starterLangs.length - 1 ? starterLangs[i + 1] : null
- createPage({
- path: slug,
- component: DEFAULT_TEMPLATE,
- context: {
- id: `${code}-starters`,
- slug: slug,
- isIndex: false,
- title: name,
- section: 'models',
- sectionTitle: sections.models.title,
- theme: sections.models.theme,
- next: next
- ? { title: next.name, slug: `/models/${next.code}-starters` }
- : null,
- meta: { models: starters, isStarters: true },
- },
- })
- })
})
)
})
diff --git a/website/src/templates/docs.js b/website/src/templates/docs.js
index 7bb62fd21..8343a16a8 100644
--- a/website/src/templates/docs.js
+++ b/website/src/templates/docs.js
@@ -52,19 +52,6 @@ const Docs = ({ pageContext, children }) => (
id: model,
})),
}))
- if (sidebar.items.length > 2) {
- sidebar.items[2].items = languages
- .filter(({ starters }) => starters && starters.length)
- .map(lang => ({
- text: lang.name,
- url: `/models/${lang.code}-starters`,
- isActive: id === `${lang.code}-starters`,
- menu: lang.starters.map(model => ({
- text: model,
- id: model,
- })),
- }))
- }
}
const sourcePath = source ? github(source) : null
const currentSource = getCurrentSource(slug, isIndex)
diff --git a/website/src/templates/models.js b/website/src/templates/models.js
index 9c6f595da..b9658dacd 100644
--- a/website/src/templates/models.js
+++ b/website/src/templates/models.js
@@ -374,7 +374,7 @@ const Models = ({ pageContext, repo, children }) => {
const [initialized, setInitialized] = useState(false)
const [compatibility, setCompatibility] = useState({})
const { id, title, meta } = pageContext
- const { models, isStarters } = meta
+ const { models } = meta
const baseUrl = `https://raw.githubusercontent.com/${repo}/master`
useEffect(() => {
@@ -388,26 +388,9 @@ const Models = ({ pageContext, repo, children }) => {
}
}, [initialized, baseUrl])
- const modelTitle = title
- const modelTeaser = `Available trained pipelines for ${title}`
- const starterTitle = `${title} starters`
- const starterTeaser = `Available transfer learning starter packs for ${title}`
-
return (
<>
-
- {isStarters && (
-
-
- Starter packs are pretrained weights you can initialize your models with to
- achieve better accuracy, like word vectors (which will be used as features
- during training).
-
-
- )}
+