diff --git a/spacy/_ml.py b/spacy/_ml.py
index 0dda71477..6723e5cf9 100644
--- a/spacy/_ml.py
+++ b/spacy/_ml.py
@@ -307,6 +307,7 @@ def PyTorchBiLSTM(nO, nI, depth, dropout=0.2):
     import torch.nn
     from thinc.api import with_square_sequences
     from thinc.extra.wrappers import PyTorchWrapperRNN
+
     if depth == 0:
         return layerize(noop())
     model = torch.nn.LSTM(nI, nO // 2, depth, bidirectional=True, dropout=dropout)
@@ -322,7 +323,7 @@ def Tok2Vec(width, embed_size, **kwargs):
     bilstm_depth = kwargs.get("bilstm_depth", 0)
 
     cols = ["ID", "NORM", "PREFIX", "SUFFIX", "SHAPE", "ORTH"]
- 
+
     doc2feats_cfg = {"arch": "spacy.Doc2Feats.v1", "config": {"columns": cols}}
     if char_embed:
         embed_cfg = {
@@ -332,13 +333,10 @@ def Tok2Vec(width, embed_size, **kwargs):
                 "chars": 6,
                 "@mix": {
                     "arch": "spacy.LayerNormalizedMaxout.v1",
-                    "config": {
-                        "width": width,
-                        "pieces": 3
-                    }
+                    "config": {"width": width, "pieces": 3},
                 },
-                "@embed_features": None
-            }
+                "@embed_features": None,
+            },
         }
     else:
         embed_cfg = {
@@ -351,12 +349,9 @@ def Tok2Vec(width, embed_size, **kwargs):
                 "@pretrained_vectors": None,
                 "@mix": {
                     "arch": "spacy.LayerNormalizedMaxout.v1",
-                    "config": {
-                        "width": width,
-                        "pieces": 3
-                    }
+                    "config": {"width": width, "pieces": 3},
                 },
-            }
+            },
         }
         if pretrained_vectors:
             embed_cfg["config"]["@pretrained_vectors"] = {
@@ -364,8 +359,8 @@ def Tok2Vec(width, embed_size, **kwargs):
                 "config": {
                     "vectors_name": pretrained_vectors,
                     "width": width,
-                    "column": cols.index(ID)
-                }
+                    "column": cols.index(ID),
+                },
             }
     cnn_cfg = {
         "arch": "spacy.MaxoutWindowEncoder.v1",
@@ -373,35 +368,26 @@ def Tok2Vec(width, embed_size, **kwargs):
             "width": width,
             "window_size": 1,
             "pieces": cnn_maxout_pieces,
-            "depth": conv_depth
-        }
+            "depth": conv_depth,
+        },
     }
 
     bilstm_cfg = {
         "arch": "spacy.TorchBiLSTMEncoder.v1",
-        "config": {
-            "width": width,
-            "depth": bilstm_depth,
-        }
+        "config": {"width": width, "depth": bilstm_depth},
     }
     if conv_depth == 0 and bilstm_depth == 0:
         encode_cfg = {}
     elif conv_depth >= 1 and bilstm_depth >= 1:
         encode_cfg = {
             "arch": "thinc.FeedForward.v1",
-            "config": {
-                "children": [cnn_cfg, bilstm_cfg]
-            }
+            "config": {"children": [cnn_cfg, bilstm_cfg]},
         }
     elif conv_depth >= 1:
         encode_cfg = cnn_cfg
     else:
         encode_cfg = bilstm_cfg
-    config = {
-        "@doc2feats": doc2feats_cfg,
-        "@embed": embed_cfg,
-        "@encode": encode_cfg
-    }
+    config = {"@doc2feats": doc2feats_cfg, "@embed": embed_cfg, "@encode": encode_cfg}
     return new_ml.Tok2Vec(config)
 
 
diff --git a/spacy/cli/train.py b/spacy/cli/train.py
index c5441a8ff..13fcae37f 100644
--- a/spacy/cli/train.py
+++ b/spacy/cli/train.py
@@ -262,8 +262,11 @@ def train(
                 exits=1,
             )
         train_docs = corpus.train_docs(
-            nlp, noise_level=noise_level, gold_preproc=gold_preproc, max_length=0,
-            ignore_misaligned=True
+            nlp,
+            noise_level=noise_level,
+            gold_preproc=gold_preproc,
+            max_length=0,
+            ignore_misaligned=True,
         )
         train_labels = set()
         if textcat_multilabel:
@@ -344,7 +347,7 @@ def train(
                 orth_variant_level=orth_variant_level,
                 gold_preproc=gold_preproc,
                 max_length=0,
-                ignore_misaligned=True
+                ignore_misaligned=True,
             )
             if raw_text:
                 random.shuffle(raw_text)
@@ -383,8 +386,11 @@ def train(
                         if hasattr(component, "cfg"):
                             component.cfg["beam_width"] = beam_width
                     dev_docs = list(
-                        corpus.dev_docs(nlp_loaded, gold_preproc=gold_preproc,
-                                        ignore_misaligned=True)
+                        corpus.dev_docs(
+                            nlp_loaded,
+                            gold_preproc=gold_preproc,
+                            ignore_misaligned=True,
+                        )
                     )
                     nwords = sum(len(doc_gold[0]) for doc_gold in dev_docs)
                     start_time = timer()
@@ -401,8 +407,11 @@ def train(
                                 if hasattr(component, "cfg"):
                                     component.cfg["beam_width"] = beam_width
                             dev_docs = list(
-                                corpus.dev_docs(nlp_loaded, gold_preproc=gold_preproc,
-                                                ignore_misaligned=True)
+                                corpus.dev_docs(
+                                    nlp_loaded,
+                                    gold_preproc=gold_preproc,
+                                    ignore_misaligned=True,
+                                )
                             )
                             start_time = timer()
                             scorer = nlp_loaded.evaluate(dev_docs, verbose=verbose)
diff --git a/spacy/language.py b/spacy/language.py
index a7d1f3a70..05838f21b 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -131,9 +131,7 @@ class Language(object):
     Defaults = BaseDefaults
     lang = None
 
-    factories = {
-        "tokenizer": lambda nlp: nlp.Defaults.create_tokenizer(nlp),
-    }
+    factories = {"tokenizer": lambda nlp: nlp.Defaults.create_tokenizer(nlp)}
 
     def __init__(
         self, vocab=True, make_doc=True, max_length=10 ** 6, meta={}, **kwargs
diff --git a/spacy/ml/__init__.py b/spacy/ml/__init__.py
index 057484590..57e7ef571 100644
--- a/spacy/ml/__init__.py
+++ b/spacy/ml/__init__.py
@@ -1 +1,5 @@
-from .tok2vec import Tok2Vec
+# coding: utf8
+from __future__ import unicode_literals
+
+from .tok2vec import Tok2Vec  # noqa: F401
+from .common import FeedForward, LayerNormalizedMaxout  # noqa: F401
diff --git a/spacy/ml/common.py b/spacy/ml/common.py
index 9c9328d72..963d4dc35 100644
--- a/spacy/ml/common.py
+++ b/spacy/ml/common.py
@@ -13,6 +13,7 @@ def FeedForward(config):
     model.cfg = config
     return model
 
+
 @register_architecture("spacy.LayerNormalizedMaxout.v1")
 def LayerNormalizedMaxout(config):
     width = config["width"]
diff --git a/spacy/ml/tok2vec.py b/spacy/ml/tok2vec.py
index e41c28ea2..d78a45191 100644
--- a/spacy/ml/tok2vec.py
+++ b/spacy/ml/tok2vec.py
@@ -9,7 +9,6 @@ from thinc.misc import Residual, LayerNorm, FeatureExtracter
 
 from ..util import make_layer, register_architecture
 from ._wire import concatenate_lists
-from .common import *
 
 
 @register_architecture("spacy.Tok2Vec.v1")
@@ -81,8 +80,7 @@ def MaxoutWindowEncoder(config):
     depth = config["depth"]
 
     cnn = chain(
-        ExtractWindow(nW=nW),
-        LayerNorm(Maxout(nO, nO * ((nW * 2) + 1), pieces=nP)),
+        ExtractWindow(nW=nW), LayerNorm(Maxout(nO, nO * ((nW * 2) + 1), pieces=nP))
     )
     model = clone(Residual(cnn), depth)
     model.nO = nO
diff --git a/spacy/tests/regression/test_issue4402.py b/spacy/tests/regression/test_issue4402.py
index d213253ed..2e1b69000 100644
--- a/spacy/tests/regression/test_issue4402.py
+++ b/spacy/tests/regression/test_issue4402.py
@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 import srsly
-from spacy.gold import GoldCorpus, json_to_tuple
+from spacy.gold import GoldCorpus
 
 from spacy.lang.en import English
 from spacy.tests.util import make_tempdir
@@ -94,4 +94,3 @@ json_data = [
         ],
     }
 ]
-
diff --git a/spacy/tests/test_gold.py b/spacy/tests/test_gold.py
index 0f3112e07..05fc95c37 100644
--- a/spacy/tests/test_gold.py
+++ b/spacy/tests/test_gold.py
@@ -205,4 +205,3 @@ def test_align(tokens_a, tokens_b, expected):
     # check symmetry
     cost, a2b, b2a, a2b_multi, b2a_multi = align(tokens_b, tokens_a)
     assert (cost, list(b2a), list(a2b), b2a_multi, a2b_multi) == expected
-
diff --git a/spacy/tests/test_misc.py b/spacy/tests/test_misc.py
index 2a92155f0..4075ccf64 100644
--- a/spacy/tests/test_misc.py
+++ b/spacy/tests/test_misc.py
@@ -96,14 +96,14 @@ def test_PrecomputableAffine(nO=4, nI=5, nF=3, nP=2):
 
 def test_prefer_gpu():
     try:
-        import cupy
+        import cupy  # noqa: F401
     except ImportError:
         assert not prefer_gpu()
 
 
 def test_require_gpu():
     try:
-        import cupy
+        import cupy  # noqa: F401
     except ImportError:
         with pytest.raises(ValueError):
             require_gpu()