Add Fenced Docstring Testing

keras_nlp/models/albert/albert_tokenizer.py

@@ -59,7 +59,7 @@ class AlbertTokenizer(SentencePieceTokenizer):
     tokenizer("the quick brown fox")
 
     # Detokenization.
-    tokenizer.detokenize(tf.constant([[[2, 14, 2231, 886, 2385, 3]]))
+    tokenizer.detokenize(tf.constant([[2, 14, 2231, 886, 2385, 3]]))
     ```
     """
 

keras_nlp/models/bert/bert_backbone.py

@@ -77,7 +77,7 @@ class BertBackbone(Backbone):
     }
 
     # Pretrained BERT encoder
-    model = keras_nlp.models.BertBackbone.from_preset("base_base_en_uncased")
+    model = keras_nlp.models.BertBackbone.from_preset("bert_base_en_uncased")
     output = model(input_data)
 
     # Randomly initialized BERT encoder with a custom config

keras_nlp/models/distil_bert/distil_bert_classifier.py

@@ -64,7 +64,7 @@ class DistilBertClassifier(PipelineModel):
     preprocessed_features = {
         "token_ids": tf.ones(shape=(2, 12), dtype=tf.int64),
         "padding_mask": tf.constant(
-            [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2, shape=(1, 12)),
+            [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2, shape=(2, 12)),
     }
     labels = [0, 3]
 
@@ -84,6 +84,9 @@ class DistilBertClassifier(PipelineModel):
         num_classes=4,
         preprocessor=None,
     )
+    classifier.compile(
+        loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
+    )
     classifier.fit(x=preprocessed_features, y=labels, batch_size=2)
 
     # Access backbone programatically (e.g., to change `trainable`)
@@ -218,7 +221,7 @@ def from_preset(
         labels = [0, 3]
 
         # Use a shorter sequence length.
-        preprocessor = keras_nlp.models.DistilBertBackbone.from_preset(
+        preprocessor = keras_nlp.models.DistilBertPreprocessor.from_preset(
             "distil_bert_base_en_uncased",
             sequence_length=128,
         )

keras_nlp/models/roberta/roberta_classifier.py

@@ -197,8 +197,8 @@ def from_preset(
         features = ["The quick brown fox jumped.", "I forgot my homework."]
         labels = [0, 3]
 
-        # Create a RobertClassifier and fit your data.
-        classifier = keras_nlp.models.RobertClassifier.from_preset(
+        # Create a RobertaClassifier and fit your data.
+        classifier = keras_nlp.models.RobertaClassifier.from_preset(
             "roberta_base_en",
             num_classes=4,
         )
@@ -215,13 +215,13 @@ def from_preset(
         labels = [0, 3]
 
         # Use a shorter sequence length.
-        preprocessor = keras_nlp.models.RobertPreprocessor.from_preset(
+        preprocessor = keras_nlp.models.RobertaPreprocessor.from_preset(
             "roberta_base_en",
             sequence_length=128,
         )
 
-        # Create a RobertClassifier and fit your data.
-        classifier = keras_nlp.models.RobertClassifier.from_preset(
+        # Create a RobertaClassifier and fit your data.
+        classifier = keras_nlp.models.RobertaClassifier.from_preset(
             "roberta_base_en",
             num_classes=4,
             preprocessor=preprocessor,
@@ -244,7 +244,7 @@ def from_preset(
         labels = [0, 3]
 
         # Create a RoBERTa classifier and fit your data.
-        classifier = keras_nlp.models.RobertClassifier.from_preset(
+        classifier = keras_nlp.models.RobertaClassifier.from_preset(
             "roberta_base_en",
             num_classes=4,
             preprocessor=None,

keras_nlp/models/roberta/roberta_preprocessor.py

@@ -242,13 +242,13 @@ def from_preset(
         Examples:
         ```python
         # Load preprocessor from preset
-        preprocessor = keras_nlp.models.RobertPreprocessor.from_preset(
+        preprocessor = keras_nlp.models.RobertaPreprocessor.from_preset(
             "roberta_base_en",
         )
         preprocessor("The quick brown fox jumped.")
 
         # Override sequence_length
-        preprocessor = keras_nlp.models.BertPreprocessor.from_preset(
+        preprocessor = keras_nlp.models.RobertaPreprocessor.from_preset(
             "roberta_base_en",
             sequence_length=64
         )

keras_nlp/models/xlm_roberta/xlm_roberta_classifier.py

@@ -62,7 +62,7 @@ class XLMRobertaClassifier(PipelineModel):
     preprocessed_features = {
         "token_ids": tf.ones(shape=(2, 12), dtype=tf.int64),
         "padding_mask": tf.constant(
-            [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2, shape=(1, 12)),
+            [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2, shape=(2, 12)),
     }
     labels = [0, 3]
 
@@ -82,6 +82,9 @@ class XLMRobertaClassifier(PipelineModel):
         num_classes=4,
         preprocessor=None,
     )
+    classifier.compile(
+        loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
+    )
     classifier.fit(x=preprocessed_features, y=labels, batch_size=2)
 
     # Access backbone programatically (e.g., to change `trainable`)

keras_nlp/models/xlm_roberta/xlm_roberta_tokenizer.py

@@ -186,7 +186,7 @@ def from_preset(
         tokenizer("The quick brown fox tripped.")
 
         # Detokenize some input.
-        tokenizer.detokenize([5, 6, 7, 8, 9])
+        tokenizer.detokenize(tf.constant([581, 63773, 119455, 6, 147797]))
         ```
         """
         if preset not in cls.presets:

keras_nlp/tests/doc_tests/docstring_test.py

@@ -13,19 +13,24 @@
 # limitations under the License.
 
 import doctest
+import io
 import os
+import re
 import sys
 import unittest
 
 import numpy as np
 import pytest
+import sentencepiece
 import tensorflow as tf
 from tensorflow import keras
 
 import keras_nlp
 from keras_nlp.tests.doc_tests import docstring_lib
+from keras_nlp.tests.doc_tests import fenced_docstring_lib
 
 PACKAGE = "keras_nlp."
+DIRECTORY = "keras_nlp"
 
 
 def find_modules():
@@ -37,6 +42,18 @@ def find_modules():
     return keras_nlp_modules
 
 
+def find_files(regex_pattern=None):
+    py_files = []
+    for root, dirs, files in os.walk(DIRECTORY):
+        for file in files:
+            file = os.path.join(root, file)
+            if file.endswith(".py"):
+                if regex_pattern is not None and regex_pattern.search(file):
+                    continue
+                py_files.append(file)
+    return py_files
+
+
 @pytest.mark.skipif(
     sys.platform == "win32", reason="Numpy prints differently on windows"
 )
@@ -77,3 +94,59 @@ def test_docstrings():
     if not result.wasSuccessful():
         print(result)
     assert result.wasSuccessful()
+
+
+@pytest.mark.skipif(
+    sys.platform == "win32", reason="Numpy prints differently on windows"
+)
+def test_fenced_docstrings():
+
+    regex_pattern = re.compile(
+        r"|".join(
+            [
+                # Endswith patterns
+                "test\\.py$",
+                "__init__\\.py$",
+                # Whole string matching
+                "^keras_nlp/models/backbone\\.py$",
+                "^keras_nlp/models/preprocessor\\.py$",
+                "^keras_nlp/models/task\\.py$",
+                # Unexported symbols
+                "deberta_v3",
+                "gpt2",
+            ]
+        )
+    )
+    keras_nlp_files = find_files(regex_pattern=regex_pattern)
+    runner = unittest.TextTestRunner()
+    suite = unittest.TestSuite()
+
+    suite.addTest(
+        doctest.DocFileSuite(
+            *keras_nlp_files,
+            module_relative=False,
+            parser=fenced_docstring_lib.FencedCellParser(fence_label="python"),
+            globs={
+                "_print_if_not_none": fenced_docstring_lib._print_if_not_none,
+                "tf": tf,
+                "np": np,
+                "os": os,
+                "keras": keras,
+                "keras_nlp": keras_nlp,
+                "io": io,
+                "sentencepiece": sentencepiece,
+            },
+            checker=fenced_docstring_lib.FencedCellOutputChecker(),
+            optionflags=(
+                doctest.ELLIPSIS
+                | doctest.NORMALIZE_WHITESPACE
+                | doctest.IGNORE_EXCEPTION_DETAIL
+                | doctest.DONT_ACCEPT_BLANKLINE
+            ),
+        )
+    )
+
+    result = runner.run(suite)
+    if not result.wasSuccessful():
+        print(result)
+    assert result.wasSuccessful()