Packages

class GPT2Transformer extends AnnotatorModel[GPT2Transformer] with HasBatchedAnnotate[GPT2Transformer] with ParamsAndFeaturesWritable with WriteTensorflowModel with WriteOnnxModel with HasEngine

GPT-2: the OpenAI Text-To-Text Transformer

GPT-2 is a large transformer-based language model with 1.5 billion parameters, trained on a dataset of 8 million web pages. GPT-2 is trained with a simple objective: predict the next word, given all of the previous words within some text. The diversity of the dataset causes this simple goal to contain naturally occurring demonstrations of many tasks across diverse domains. GPT-2 is a direct scale-up of GPT, with more than 10X the parameters and trained on more than 10X the amount of data.

GPT-2 displays a broad set of capabilities, including the ability to generate conditional synthetic text samples of unprecedented quality, where we prime the model with an input and have it generate a lengthy continuation. In addition, GPT-2 outperforms other language models trained on specific domains (like Wikipedia, news, or books) without needing to use these domain-specific training datasets. On language tasks like question answering, reading comprehension, summarization, and translation, GPT-2 begins to learn these tasks from the raw text, using no task-specific training data. While scores on these downstream tasks are far from state-of-the-art, they suggest that the tasks can benefit from unsupervised techniques, given sufficient (unlabeled) data and compute.

Pretrained models can be loaded with pretrained of the companion object:

val gpt2 = GPT2Transformer.pretrained()
  .setInputCols("document")
  .setOutputCol("generation")

The default model is "gpt2", if no name is provided. For available pretrained models please see the Models Hub.

For extended examples of usage, see GPT2TestSpec.

References:

Paper Abstract:

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets. We demonstrate that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText. When conditioned on a document plus questions, the answers generated by the language model reach F1 on the CoQA dataset - matching or exceeding the performance of 3 out of 4 baseline systems without using the 127,000+ training examples. The capacity of the language model is essential to the success of zero-shot task transfer and increasing it improves performance in a log-linear fashion across tasks. Our largest model, GPT-2, is a 1.5B parameter Transformer that achieves state of the art results on 7 out of 8 tested language modeling datasets in a zero-shot setting but still underfits WebText. Samples from the model reflect these improvements and contain coherent paragraphs of text. These findings suggest a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations.

Note:

This is a very computationally expensive module especially on larger sequence. The use of an accelerator such as GPU is recommended.

Example

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.seq2seq.GPT2Transformer
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("documents")

val gpt2 = GPT2Transformer.pretrained("gpt2")
  .setInputCols(Array("documents"))
  .setMinOutputLength(10)
  .setMaxOutputLength(50)
  .setDoSample(false)
  .setTopK(50)
  .setNoRepeatNgramSize(3)
  .setOutputCol("generation")

val pipeline = new Pipeline().setStages(Array(documentAssembler, gpt2))

val data = Seq(
  "My name is Leonardo."
).toDF("text")
val result = pipeline.fit(data).transform(data)

results.select("generation.result").show(truncate = false)
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|result                                                                                                                                                                                              |
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|[ My name is Leonardo. I am a man of letters. I have been a man for many years. I was born in the year 1776. I came to the United States in 1776, and I have lived in the United Kingdom since 1776]|
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
Linear Supertypes
HasEngine, WriteOnnxModel, WriteTensorflowModel, HasBatchedAnnotate[GPT2Transformer], AnnotatorModel[GPT2Transformer], CanBeLazy, RawAnnotator[GPT2Transformer], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[GPT2Transformer], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. GPT2Transformer
  2. HasEngine
  3. WriteOnnxModel
  4. WriteTensorflowModel
  5. HasBatchedAnnotate
  6. AnnotatorModel
  7. CanBeLazy
  8. RawAnnotator
  9. HasOutputAnnotationCol
  10. HasInputAnnotationCols
  11. HasOutputAnnotatorType
  12. ParamsAndFeaturesWritable
  13. HasFeatures
  14. DefaultParamsWritable
  15. MLWritable
  16. Model
  17. Transformer
  18. PipelineStage
  19. Logging
  20. Params
  21. Serializable
  22. Serializable
  23. Identifiable
  24. AnyRef
  25. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new GPT2Transformer()
  2. new GPT2Transformer(uid: String)

    uid

    required uid for storing annotator to disk

Type Members

  1. type AnnotationContent = Seq[Row]

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  12. def batchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[Seq[Annotation]]

    takes a document and annotations and produces new annotations of this annotator's annotation type

    takes a document and annotations and produces new annotations of this annotator's annotation type

    batchedAnnotations

    Annotations that correspond to inputAnnotationCols generated by previous annotators if any

    returns

    any number of annotations processed for every input annotation. Not necessary one to one relationship

    Definition Classes
    GPT2Transformer → HasBatchedAnnotate
  13. def batchProcess(rows: Iterator[_]): Iterator[Row]
    Definition Classes
    HasBatchedAnnotate
  14. val batchSize: IntParam

    Size of every batch (Default depends on model).

    Size of every batch (Default depends on model).

    Definition Classes
    HasBatchedAnnotate
  15. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  16. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  17. final def clear(param: Param[_]): GPT2Transformer.this.type
    Definition Classes
    Params
  18. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  19. val configProtoBytes: IntArrayParam

    ConfigProto from tensorflow, serialized into byte array.

    ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()

  20. def copy(extra: ParamMap): GPT2Transformer

    requirement for annotators copies

    requirement for annotators copies

    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  21. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  22. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. val doSample: BooleanParam

    Whether or not to use sampling, use greedy decoding otherwise (Default: false)

  24. val engine: Param[String]

    This param is set internally once via loadSavedModel.

    This param is set internally once via loadSavedModel. That's why there is no setter

    Definition Classes
    HasEngine
  25. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  26. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  27. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  28. def explainParams(): String
    Definition Classes
    Params
  29. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  30. def extraValidateMsg: String

    Override for additional custom schema checks

    Override for additional custom schema checks

    Attributes
    protected
    Definition Classes
    RawAnnotator
  31. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  32. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  33. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  34. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  35. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  40. def getBatchSize: Int

    Size of every batch.

    Size of every batch.

    Definition Classes
    HasBatchedAnnotate
  41. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  42. def getConfigProtoBytes: Option[Array[Byte]]

  43. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  44. def getDoSample: Boolean

  45. def getEngine: String

    Definition Classes
    HasEngine
  46. def getIgnoreTokenIds: Array[Int]

  47. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  48. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  49. def getMaxOutputLength: Int

  50. def getMinOutputLength: Int

  51. def getModelIfNotSet: GPT2

  52. def getNoRepeatNgramSize: Int

  53. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  54. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  55. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  56. def getRandomSeed: Option[Int]

  57. def getRepetitionPenalty: Double

  58. def getTemperature: Double

  59. def getTopK: Int

  60. def getTopP: Double

  61. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  62. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  63. def hasParent: Boolean
    Definition Classes
    Model
  64. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  65. var ignoreTokenIds: IntArrayParam

    A list of token ids which are ignored in the decoder's output (Default: Array())

  66. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  67. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator type : DOCUMENT

    Input annotator type : DOCUMENT

    Definition Classes
    GPT2Transformer → HasInputAnnotationCols
  69. final val inputCols: StringArrayParam

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  70. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  71. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  72. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  73. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  74. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  75. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  76. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  81. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  82. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  83. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  84. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  85. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  86. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  87. val maxOutputLength: IntParam

    Maximum length of the sequence to be generated (Default: 20)

  88. val merges: MapFeature[(String, String), Int]

    Holding merges.txt coming from RoBERTa model

  89. val minOutputLength: IntParam

    Minimum length of the sequence to be generated (Default: 0)

  90. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  91. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  92. val noRepeatNgramSize: IntParam

    If set to int > 0, all ngrams of that size can only occur once (Default: 0)

  93. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  94. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  95. def onWrite(path: String, spark: SparkSession): Unit
    Definition Classes
    GPT2Transformer → ParamsAndFeaturesWritable
  96. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  97. val outputAnnotatorType: String

    Output annotator type : DOCUMENT

    Output annotator type : DOCUMENT

    Definition Classes
    GPT2Transformer → HasOutputAnnotatorType
  98. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  99. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  100. var parent: Estimator[GPT2Transformer]
    Definition Classes
    Model
  101. var randomSeed: Option[Int]

    Optional Random seed for the model.

    Optional Random seed for the model. Needs to be of type Long.

  102. val repetitionPenalty: DoubleParam

    The parameter for repetition penalty (Default: 1.0).

    The parameter for repetition penalty (Default: 1.0). 1.0 means no penalty. See this paper for more details.

  103. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  104. def set[T](feature: StructFeature[T], value: T): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  105. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  106. def set[T](feature: SetFeature[T], value: Set[T]): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  107. def set[T](feature: ArrayFeature[T], value: Array[T]): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  108. final def set(paramPair: ParamPair[_]): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    Params
  109. final def set(param: String, value: Any): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    Params
  110. final def set[T](param: Param[T], value: T): GPT2Transformer.this.type
    Definition Classes
    Params
  111. def setBatchSize(size: Int): GPT2Transformer.this.type

    Size of every batch.

    Size of every batch.

    Definition Classes
    HasBatchedAnnotate
  112. def setConfigProtoBytes(bytes: Array[Int]): GPT2Transformer.this.type

  113. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  114. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  115. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  116. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  117. final def setDefault(paramPairs: ParamPair[_]*): GPT2Transformer.this.type
    Attributes
    protected
    Definition Classes
    Params
  118. final def setDefault[T](param: Param[T], value: T): GPT2Transformer.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  119. def setDoSample(value: Boolean): GPT2Transformer.this.type

  120. def setIgnoreTokenIds(tokenIds: Array[Int]): GPT2Transformer.this.type

  121. final def setInputCols(value: String*): GPT2Transformer.this.type
    Definition Classes
    HasInputAnnotationCols
  122. def setInputCols(value: Array[String]): GPT2Transformer.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  123. def setLazyAnnotator(value: Boolean): GPT2Transformer.this.type
    Definition Classes
    CanBeLazy
  124. def setMaxOutputLength(value: Int): GPT2Transformer.this.type

  125. def setMerges(value: Map[(String, String), Int]): GPT2Transformer.this.type

  126. def setMinOutputLength(value: Int): GPT2Transformer.this.type

  127. def setModelIfNotSet(spark: SparkSession, tfWrapper: Option[TensorflowWrapper], onnxWrapper: Option[OnnxWrapper]): GPT2Transformer.this.type

  128. def setNoRepeatNgramSize(value: Int): GPT2Transformer.this.type

  129. final def setOutputCol(value: String): GPT2Transformer.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  130. def setParent(parent: Estimator[GPT2Transformer]): GPT2Transformer
    Definition Classes
    Model
  131. def setRandomSeed(value: Int): GPT2Transformer.this.type

  132. def setRepetitionPenalty(value: Double): GPT2Transformer.this.type

  133. def setTask(value: String): GPT2Transformer.this.type

  134. def setTemperature(value: Double): GPT2Transformer.this.type

  135. def setTopK(value: Int): GPT2Transformer.this.type

  136. def setTopP(value: Double): GPT2Transformer.this.type

  137. def setVocabulary(value: Map[String, Int]): GPT2Transformer.this.type

  138. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  139. val task: Param[String]

    Set transformer task, e.g.

    Set transformer task, e.g. "summarize:" (Default: "").

  140. val temperature: DoubleParam

    The value used to module the next token probabilities (Default: 1.0)

  141. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  142. val topK: IntParam

    The number of highest probability vocabulary tokens to keep for top-k-filtering (Default: 50)

  143. val topP: DoubleParam

    If set to float < 1.0, only the most probable tokens with probabilities that add up to topP or higher are kept for generation (Default: 1.0)

  144. final def transform(dataset: Dataset[_]): DataFrame

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    dataset

    Dataset[Row]

    Definition Classes
    AnnotatorModel → Transformer
  145. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  146. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  147. final def transformSchema(schema: StructType): StructType

    requirement for pipeline transformation validation.

    requirement for pipeline transformation validation. It is called on fit()

    Definition Classes
    RawAnnotator → PipelineStage
  148. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  149. val uid: String
    Definition Classes
    GPT2Transformer → Identifiable
  150. def validate(schema: StructType): Boolean

    takes a Dataset and checks to see if all the required annotation types are present.

    takes a Dataset and checks to see if all the required annotation types are present.

    schema

    to be validated

    returns

    True if all the required types are present, else false

    Attributes
    protected
    Definition Classes
    RawAnnotator
  151. val vocabulary: MapFeature[String, Int]

    Vocabulary used to encode the words to ids with bpeTokenizer.encode

  152. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  153. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  154. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  155. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  156. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
  157. def writeOnnxModel(path: String, spark: SparkSession, onnxWrapper: OnnxWrapper, suffix: String, fileName: String): Unit
    Definition Classes
    WriteOnnxModel
  158. def writeOnnxModels(path: String, spark: SparkSession, onnxWrappersWithNames: Seq[(OnnxWrapper, String)], suffix: String): Unit
    Definition Classes
    WriteOnnxModel
  159. def writeTensorflowHub(path: String, tfPath: String, spark: SparkSession, suffix: String = "_use"): Unit
    Definition Classes
    WriteTensorflowModel
  160. def writeTensorflowModel(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None): Unit
    Definition Classes
    WriteTensorflowModel
  161. def writeTensorflowModelV2(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None, savedSignatures: Option[Map[String, String]] = None): Unit
    Definition Classes
    WriteTensorflowModel

Inherited from HasEngine

Inherited from WriteOnnxModel

Inherited from WriteTensorflowModel

Inherited from HasBatchedAnnotate[GPT2Transformer]

Inherited from AnnotatorModel[GPT2Transformer]

Inherited from CanBeLazy

Inherited from RawAnnotator[GPT2Transformer]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[GPT2Transformer]

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

A list of (hyper-)parameter keys this annotator can take. Users can set and get the parameter values through setters and getters, respectively.

Members

Parameter setters

Parameter getters