spark-nlp 2.6.3rc1__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/annotator/classifier_dl/classifier_dl.py

@@ -0,0 +1,320 @@
+#  Copyright 2017-2022 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Contains classes for ClassifierDL."""
+
+from sparknlp.annotator.param import EvaluationDLParams, ClassifierEncoder
+from sparknlp.base import DocumentAssembler
+from sparknlp.common import *
+
+
+class ClassifierDLApproach(AnnotatorApproach, EvaluationDLParams, ClassifierEncoder):
+    """Trains a ClassifierDL for generic Multi-class Text Classification.
+
+    ClassifierDL uses the state-of-the-art Universal Sentence Encoder as an
+    input for text classifications.
+    The ClassifierDL annotator uses a deep learning model (DNNs) we have built
+    inside TensorFlow and supports up to 100 classes.
+
+    For instantiated/pretrained models, see :class:`.ClassifierDLModel`.
+
+    Setting a test dataset to monitor model metrics can be done with
+    ``.setTestDataset``. The method expects a path to a parquet file containing a
+    dataframe that has the same required columns as the training dataframe. The
+    pre-processing steps for the training dataframe should also be applied to the test
+    dataframe. The following example will show how to create the test dataset:
+
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> embeddings = UniversalSentenceEncoder.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("sentence_embeddings")
+    >>> preProcessingPipeline = Pipeline().setStages([documentAssembler, embeddings])
+    >>> (train, test) = data.randomSplit([0.8, 0.2])
+    >>> preProcessingPipeline \\
+    ...     .fit(test) \\
+    ...     .transform(test)
+    ...     .write \\
+    ...     .mode("overwrite") \\
+    ...     .parquet("test_data")
+    >>> classifier = ClassifierDLApproach() \\
+    ...     .setInputCols(["sentence_embeddings"]) \\
+    ...     .setOutputCol("category") \\
+    ...     .setLabelColumn("label") \\
+    ...     .setTestDataset("test_data")
+
+    For extended examples of usage, see the Examples
+    `Examples  <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/classification/ClassifierDL_Train_multi_class_news_category_classifier.ipynb>`__.
+
+    ======================= ======================
+    Input Annotation types  Output Annotation type
+    ======================= ======================
+    ``SENTENCE_EMBEDDINGS`` ``CATEGORY``
+    ======================= ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size, by default 64
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    dropout
+        Dropout coefficient, by default 0.5
+    enableOutputLogs
+        Whether to use stdout in addition to Spark logs, by default False
+    evaluationLogExtended
+        Whether logs for validation to be extended: it displays time and evaluation of
+        each label. Default is False.
+    labelColumn
+        Column with label per each token
+    lr
+        Learning Rate, by default 0.005
+    maxEpochs
+        Maximum number of epochs to train, by default 30
+    outputLogsPath
+        Folder path to save training logs
+    randomSeed
+        Random seed for shuffling
+    testDataset
+        Path to test dataset. If set used to calculate statistic on it during training.
+    validationSplit
+        Choose the proportion of training dataset to be validated against the
+        model on each Epoch. The value should be between 0.0 and 1.0 and by
+        default it is 0.0 and off.
+    verbose
+        Level of verbosity during training
+
+    Notes
+    -----
+    - This annotator accepts a label column of a single item in either type of
+      String, Int, Float, or Double.
+    - UniversalSentenceEncoder, Transformer based embeddings, or
+      SentenceEmbeddings can be used for the ``inputCol``.
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+
+    In this example, the training data ``"sentiment.csv"`` has the form of::
+
+        text,label
+        This movie is the best movie I have wached ever! In my opinion this movie can win an award.,0
+        This was a terrible movie! The acting was bad really bad!,1
+        ...
+
+    Then traning can be done like so:
+
+    >>> smallCorpus = spark.read.option("header","True").csv("src/test/resources/classifier/sentiment.csv")
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> useEmbeddings = UniversalSentenceEncoder.pretrained() \\
+    ...     .setInputCols("document") \\
+    ...     .setOutputCol("sentence_embeddings")
+    >>> docClassifier = ClassifierDLApproach() \\
+    ...     .setInputCols("sentence_embeddings") \\
+    ...     .setOutputCol("category") \\
+    ...     .setLabelColumn("label") \\
+    ...     .setBatchSize(64) \\
+    ...     .setMaxEpochs(20) \\
+    ...     .setLr(5e-3) \\
+    ...     .setDropout(0.5)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     useEmbeddings,
+    ...     docClassifier
+    ... ])
+    >>> pipelineModel = pipeline.fit(smallCorpus)
+
+    See Also
+    --------
+    MultiClassifierDLApproach : for multi-class classification
+    SentimentDLApproach : for sentiment analysis
+    """
+    inputAnnotatorTypes = [AnnotatorType.SENTENCE_EMBEDDINGS]
+
+    outputAnnotatorType = AnnotatorType.CATEGORY
+
+    dropout = Param(Params._dummy(), "dropout", "Dropout coefficient", TypeConverters.toFloat)
+
+    def setDropout(self, v):
+        """Sets dropout coefficient, by default 0.5
+
+        Parameters
+        ----------
+        v : float
+            Dropout coefficient
+        """
+        self._set(dropout=v)
+        return self
+
+    def _create_model(self, java_model):
+        return ClassifierDLModel(java_model=java_model)
+
+    @keyword_only
+    def __init__(self):
+        super(ClassifierDLApproach, self).__init__(
+            classname="com.johnsnowlabs.nlp.annotators.classifier.dl.ClassifierDLApproach")
+        self._setDefault(
+            maxEpochs=30,
+            lr=float(0.005),
+            batchSize=64,
+            dropout=float(0.5),
+            enableOutputLogs=False,
+            evaluationLogExtended=False
+        )
+
+
+class ClassifierDLModel(AnnotatorModel, HasStorageRef, HasEngine):
+    """ClassifierDL for generic Multi-class Text Classification.
+
+    ClassifierDL uses the state-of-the-art Universal Sentence Encoder as an
+    input for text classifications. The ClassifierDL annotator uses a deep
+    learning model (DNNs) we have built inside TensorFlow and supports up to
+    100 classes.
+
+    This is the instantiated model of the :class:`.ClassifierDLApproach`.
+    For training your own model, please see the documentation of that class.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> classifierDL = ClassifierDLModel.pretrained() \\
+    ...     .setInputCols(["sentence_embeddings"]) \\
+    ...     .setOutputCol("classification")
+
+    The default model is ``"classifierdl_use_trec6"``, if no name is provided.
+    It uses embeddings from the UniversalSentenceEncoder and is trained on the
+    `TREC-6 <https://deepai.org/dataset/trec-6#:~:text=The%20TREC%20dataset%20is%20dataset,50%20has%20finer%2Dgrained%20labels>`__
+    dataset.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?task=Text+Classification>`__.
+
+    For extended examples of usage, see the
+    `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/classification/ClassifierDL_Train_multi_class_news_category_classifier.ipynb>`__.
+
+    ======================= ======================
+    Input Annotation types  Output Annotation type
+    ======================= ======================
+    ``SENTENCE_EMBEDDINGS`` ``CATEGORY``
+    ======================= ======================
+
+    Parameters
+    ----------
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    classes
+        Get the tags used to trained this ClassifierDLModel
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> sentence = SentenceDetector() \\
+    ...     .setInputCols("document") \\
+    ...     .setOutputCol("sentence")
+    >>> useEmbeddings = UniversalSentenceEncoder.pretrained() \\
+    ...     .setInputCols("document") \\
+    ...     .setOutputCol("sentence_embeddings")
+    >>> sarcasmDL = ClassifierDLModel.pretrained("classifierdl_use_sarcasm") \\
+    ...     .setInputCols("sentence_embeddings") \\
+    ...     .setOutputCol("sarcasm")
+    >>> pipeline = Pipeline() \\
+    ...     .setStages([
+    ...       documentAssembler,
+    ...       sentence,
+    ...       useEmbeddings,
+    ...       sarcasmDL
+    ...     ])
+    >>> data = spark.createDataFrame([
+    ...     ["I'm ready!"],
+    ...     ["If I could put into words how much I love waking up at 6 am on Mondays I would."]
+    ... ]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(arrays_zip(sentence, sarcasm)) as out") \\
+    ...     .selectExpr("out.sentence.result as sentence", "out.sarcasm.result as sarcasm") \\
+    ...     .show(truncate=False)
+    +-------------------------------------------------------------------------------+-------+
+    |sentence                                                                       |sarcasm|
+    +-------------------------------------------------------------------------------+-------+
+    |I'm ready!                                                                     |normal |
+    |If I could put into words how much I love waking up at 6 am on Mondays I would.|sarcasm|
+    +-------------------------------------------------------------------------------+-------+
+
+    See Also
+    --------
+    MultiClassifierDLModel : for multi-class classification
+    SentimentDLModel : for sentiment analysis
+    """
+
+    name = "ClassifierDLModel"
+
+    inputAnnotatorTypes = [AnnotatorType.SENTENCE_EMBEDDINGS]
+
+    outputAnnotatorType = AnnotatorType.CATEGORY
+
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.ClassifierDLModel", java_model=None):
+        super(ClassifierDLModel, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+
+    configProtoBytes = Param(Params._dummy(), "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    classes = Param(Params._dummy(), "classes",
+                    "get the tags used to trained this ClassifierDLModel",
+                    TypeConverters.toListString)
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    @staticmethod
+    def pretrained(name="classifierdl_use_trec6", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "classifierdl_use_trec6"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        ClassifierDLModel
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(ClassifierDLModel, name, lang, remote_loc)

sparknlp/annotator/classifier_dl/deberta_for_question_answering.py

@@ -0,0 +1,168 @@
+#  Copyright 2017-2022 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+from sparknlp.common import *
+
+
+class DeBertaForQuestionAnswering(AnnotatorModel,
+                                  HasCaseSensitiveProperties,
+                                  HasBatchedAnnotate,
+                                  HasEngine,
+                                  HasMaxSentenceLengthLimit):
+    """DeBertaForQuestionAnswering can load DeBERTa Models with a span classification head on top for extractive
+    question-answering tasks like SQuAD (a linear layer on top of the hidden-states output to compute span start
+    logits and span end logits).
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> spanClassifier = DeBertaForQuestionAnswering.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"deberta_v3_xsmall_qa_squad2"``, if no name is
+    provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Question+Answering>`__.
+
+    To see which models are compatible and how to import them see
+    `Import Transformers into Spark NLP 🚀
+    <https://github.com/JohnSnowLabs/spark-nlp/discussions/5669>`_.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT, DOCUMENT``    ``CHUNK``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more
+        memory, by default 8
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default
+        False
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    maxSentenceLength
+        Max sentence length to process, by default 128
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = MultiDocumentAssembler() \\
+    ...     .setInputCols(["question", "context"]) \\
+    ...     .setOutputCol(["document_question", "document_context"])
+    >>> spanClassifier = DeBertaForQuestionAnswering.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer") \\
+    ...     .setCaseSensitive(False)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     spanClassifier
+    ... ])
+    >>> data = spark.createDataFrame([["What's my name?", "My name is Clara and I live in Berkeley."]]).toDF("question", "context")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("answer.result").show(truncate=False)
+    +--------------------+
+    |result              |
+    +--------------------+
+    |[Clara]             |
+    +--------------------+
+    """
+    name = "DeBertaForQuestionAnswering"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    coalesceSentences = Param(Params._dummy(), "coalesceSentences",
+                              "Instead of 1 class per sentence (if inputCols is '''sentence''') output 1 class per document by averaging probabilities in all sentences.",
+                              TypeConverters.toBoolean)
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.DeBertaForQuestionAnswering",
+                 java_model=None):
+        super(DeBertaForQuestionAnswering, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=8,
+            maxSentenceLength=128,
+            caseSensitive=False
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        DeBertaForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.internal import _DeBertaQuestionAnsweringLoader
+        jModel = _DeBertaQuestionAnsweringLoader(folder, spark_session._jsparkSession)._java_obj
+        return DeBertaForQuestionAnswering(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="deberta_v3_xsmall_qa_squad2", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "deberta_v3_xsmall_qa_squad2"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        DeBertaForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(DeBertaForQuestionAnswering, name, lang, remote_loc)

sparknlp/annotator/classifier_dl/deberta_for_sequence_classification.py

@@ -0,0 +1,198 @@
+#  Copyright 2017-2022 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Contains classes for DeBertaForSequenceClassification."""
+from sparknlp.common import *
+
+
+class DeBertaForSequenceClassification(AnnotatorModel,
+                                       HasCaseSensitiveProperties,
+                                       HasBatchedAnnotate,
+                                       HasClassifierActivationProperties,
+                                       HasEngine,
+                                       HasMaxSentenceLengthLimit):
+    """DeBertaForSequenceClassification can load DeBERTa v2 & v3 Models with sequence classification/regression head on
+    top (a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> sequenceClassifier = DeBertaForSequenceClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label")
+
+    The default model is ``"deberta_v3_xsmall_sequence_classifier_imdb"``, if no name is
+    provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Text+Classification>`__.
+
+    To see which models are compatible and how to import them see
+    `Import Transformers into Spark NLP 🚀
+    <https://github.com/JohnSnowLabs/spark-nlp/discussions/5669>`_.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT, TOKEN``    ``CATEGORY``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more
+        memory, by default 8
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default
+        True
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    maxSentenceLength
+        Max sentence length to process, by default 128
+    coalesceSentences
+        Instead of 1 class per sentence (if inputCols is `sentence`) output
+        1 class per document by averaging probabilities in all sentences, by
+        default False.
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> tokenizer = Tokenizer() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("token")
+    >>> sequenceClassifier = DeBertaForSequenceClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label") \\
+    ...     .setCaseSensitive(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     tokenizer,
+    ...     sequenceClassifier
+    ... ])
+    >>> data = spark.createDataFrame([["I loved this movie when I was a child.", "It was pretty boring."]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("label.result").show(truncate=False)
+    +------+
+    |result|
+    +------+
+    |[pos] |
+    |[neg] |
+    +------+
+    """
+    name = "DeBertaForSequenceClassification"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.TOKEN]
+
+    outputAnnotatorType = AnnotatorType.CATEGORY
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    coalesceSentences = Param(Params._dummy(), "coalesceSentences",
+                              "Instead of 1 class per sentence (if inputCols is '''sentence''') output 1 class per document by averaging probabilities in all sentences.",
+                              TypeConverters.toBoolean)
+
+    def getClasses(self):
+        """
+        Returns labels used to train this model
+        """
+        return self._call_java("getClasses")
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    def setCoalesceSentences(self, value):
+        """Instead of 1 class per sentence (if inputCols is '''sentence''') output 1 class per document by averaging
+        probabilities in all sentences. Due to max sequence length limit in almost all transformer models such as
+        BERT (512 tokens), this parameter helps to feed all the sentences into the model and averaging all the
+        probabilities for the entire document instead of probabilities per sentence. (Default: true)
+
+        Parameters
+        ----------
+        value : bool
+            If the output of all sentences will be averaged to one output
+        """
+        return self._set(coalesceSentences=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.DeBertaForSequenceClassification",
+                 java_model=None):
+        super(DeBertaForSequenceClassification, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=8,
+            maxSentenceLength=128,
+            caseSensitive=True,
+            coalesceSentences=False,
+            activation="softmax"
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        AlbertForSequenceClassification
+            The restored model
+        """
+        from sparknlp.internal import _DeBertaSequenceClassifierLoader
+        jModel = _DeBertaSequenceClassifierLoader(folder, spark_session._jsparkSession)._java_obj
+        return DeBertaForSequenceClassification(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="deberta_base_sequence_classifier_imdb", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "deberta_v3_xsmall_sequence_classifier_imdb"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        AlbertForSequenceClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(DeBertaForSequenceClassification, name, lang, remote_loc)