Packages

class MLLamaForMultimodal extends AnnotatorModel[MLLamaForMultimodal] with HasBatchedAnnotateImage[MLLamaForMultimodal] with HasImageFeatureProperties with WriteOpenvinoModel with HasGeneratorProperties with HasEngine

MLLamaForMultimodal can load LLAMA 3.2 Vision models for visual question answering. The model consists of a vision encoder, a text encoder as well as a text decoder. The vision encoder will encode the input image, the text encoder will encode the input question together with the encoding of the image, and the text decoder will output the answer to the question.

The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text + images in / text out). The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The models outperform many of the available open source and closed multimodal models on common industry benchmarks.

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

val visualQA = MLLamaForMultimodal.pretrained()
  .setInputCols("image_assembler")
  .setOutputCol("answer")

The default model is "llama_3_2_11b_vision_instruct_int4", if no name is provided.

For available pretrained models please see the Models Hub.

Models from the HuggingFace 🤗 Transformers library are also compatible with Spark NLP 🚀. To see which models are compatible and how to import them see https://github.com/JohnSnowLabs/spark-nlp/discussions/5669 and to see more extended examples, see https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/annotators/cv/MLLamaForMultimodalTest.scala.

Example

import spark.implicits._
import com.johnsnowlabs.nlp.base._
import com.johnsnowlabs.nlp.annotator._
import org.apache.spark.ml.Pipeline

val imageDF: DataFrame = ResourceHelper.spark.read
 .format("image")
 .option("dropInvalid", value = true)
 .load(imageFolder)

val testDF: DataFrame = imageDF.withColumn("text", lit("<|begin_of_text|><|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n<|image|>What is unusual on this image?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"))

val imageAssembler: ImageAssembler = new ImageAssembler()
  .setInputCol("image")
  .setOutputCol("image_assembler")

val visualQAClassifier = MLLamaForMultimodal.pretrained()
  .setInputCols("image_assembler")
  .setOutputCol("answer")

val pipeline = new Pipeline().setStages(Array(
  imageAssembler,
  visualQAClassifier
))

val result = pipeline.fit(testDF).transform(testDF)

result.select("image_assembler.origin", "answer.result").show(false)
+--------------------------------------+------+
|origin                                |result|
+--------------------------------------+------+
|[file:///content/images/cat_image.jpg]|[The unusual aspect of this picture is the presence of two cats lying on a pink couch]|
+--------------------------------------+------+
See also

CLIPForZeroShotClassification for Zero Shot Image Classifier

Annotators Main Page for a list of transformer based classifiers

Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. MLLamaForMultimodal
  2. HasEngine
  3. HasGeneratorProperties
  4. WriteOpenvinoModel
  5. HasImageFeatureProperties
  6. HasBatchedAnnotateImage
  7. AnnotatorModel
  8. CanBeLazy
  9. RawAnnotator
  10. HasOutputAnnotationCol
  11. HasInputAnnotationCols
  12. HasOutputAnnotatorType
  13. ParamsAndFeaturesWritable
  14. HasFeatures
  15. DefaultParamsWritable
  16. MLWritable
  17. Model
  18. Transformer
  19. PipelineStage
  20. Logging
  21. Params
  22. Serializable
  23. Serializable
  24. Identifiable
  25. AnyRef
  26. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new MLLamaForMultimodal()

    Annotator reference id.

    Annotator reference id. Used to identify elements in metadata or to refer to this annotator type

  2. new MLLamaForMultimodal(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. val addedTokens: MapFeature[String, Int]

    Additional tokens to be added to the vocabulary

  11. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. def batchAnnotate(batchedAnnotations: Seq[Array[AnnotationImage]]): 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 in batches that correspond to inputAnnotationCols generated by previous annotators if any

    returns

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

    Definition Classes
    MLLamaForMultimodalHasBatchedAnnotateImage
  14. def batchProcess(rows: Iterator[_]): Iterator[Row]
    Definition Classes
    HasBatchedAnnotateImage
  15. val batchSize: IntParam

    Size of every batch (Default depends on model).

    Size of every batch (Default depends on model).

    Definition Classes
    HasBatchedAnnotateImage
  16. val beamSize: IntParam

    Beam size for the beam search algorithm (Default: 4)

    Beam size for the beam search algorithm (Default: 4)

    Definition Classes
    HasGeneratorProperties
  17. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  18. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  19. final def clear(param: Param[_]): MLLamaForMultimodal.this.type
    Definition Classes
    Params
  20. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  21. def copy(extra: ParamMap): MLLamaForMultimodal

    requirement for annotators copies

    requirement for annotators copies

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

    Whether or not to normalize the input with mean and standard deviation

    Whether or not to normalize the input with mean and standard deviation

    Definition Classes
    HasImageFeatureProperties
  25. val doResize: BooleanParam

    Whether to resize the input to a certain size

    Whether to resize the input to a certain size

    Definition Classes
    HasImageFeatureProperties
  26. val doSample: BooleanParam

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

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

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

    Override for additional custom schema checks

    Override for additional custom schema checks

    Attributes
    protected
    Definition Classes
    RawAnnotator
  34. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  35. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  36. val featureExtractorType: Param[String]

    Name of model's architecture for feature extraction

    Name of model's architecture for feature extraction

    Definition Classes
    HasImageFeatureProperties
  37. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  38. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  39. val generationConfig: StructFeature[GenerationConfig]
  40. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  41. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  42. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  43. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  44. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  45. def getBatchSize: Int

    Size of every batch.

    Size of every batch.

    Definition Classes
    HasBatchedAnnotateImage
  46. def getBeamSize: Int

    Definition Classes
    HasGeneratorProperties
  47. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  48. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  49. def getDoNormalize: Boolean

    Definition Classes
    HasImageFeatureProperties
  50. def getDoResize: Boolean

    Definition Classes
    HasImageFeatureProperties
  51. def getDoSample: Boolean

    Definition Classes
    HasGeneratorProperties
  52. def getEngine: String

    Definition Classes
    HasEngine
  53. def getFeatureExtractorType: String

    Definition Classes
    HasImageFeatureProperties
  54. def getGenerationConfig: GenerationConfig
  55. def getIgnoreTokenIds: Array[Int]

  56. def getImageMean: Array[Double]

    Definition Classes
    HasImageFeatureProperties
  57. def getImageStd: Array[Double]

    Definition Classes
    HasImageFeatureProperties
  58. def getImageToken: Int

  59. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  60. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  61. def getMaxImageTiles: Int

  62. def getMaxOutputLength: Int

    Definition Classes
    HasGeneratorProperties
  63. def getMinOutputLength: Int

    Definition Classes
    HasGeneratorProperties
  64. def getModelIfNotSet: MLLama

  65. def getNReturnSequences: Int

    Definition Classes
    HasGeneratorProperties
  66. def getNoRepeatNgramSize: Int

    Definition Classes
    HasGeneratorProperties
  67. def getNumVisionTokens: Int

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

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  70. def getPaddingConstant: Int

  71. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  72. def getRandomSeed: Option[Long]

    Definition Classes
    HasGeneratorProperties
  73. def getRepetitionPenalty: Double

    Definition Classes
    HasGeneratorProperties
  74. def getResample: Int

    Definition Classes
    HasImageFeatureProperties
  75. def getSize: Int

    Definition Classes
    HasImageFeatureProperties
  76. def getStopTokenIds: Array[Int]

  77. def getTask: Option[String]

    Definition Classes
    HasGeneratorProperties
  78. def getTemperature: Double

    Definition Classes
    HasGeneratorProperties
  79. def getTopK: Int

    Definition Classes
    HasGeneratorProperties
  80. def getTopP: Double

    Definition Classes
    HasGeneratorProperties
  81. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  82. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  83. def hasParent: Boolean
    Definition Classes
    Model
  84. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  85. var ignoreTokenIds: IntArrayParam

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

  86. val imageMean: DoubleArrayParam

    The sequence of means for each channel, to be used when normalizing images

    The sequence of means for each channel, to be used when normalizing images

    Definition Classes
    HasImageFeatureProperties
  87. val imageStd: DoubleArrayParam

    The sequence of standard deviations for each channel, to be used when normalizing images

    The sequence of standard deviations for each channel, to be used when normalizing images

    Definition Classes
    HasImageFeatureProperties
  88. val imageToken: IntParam
  89. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  90. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  91. val inputAnnotatorTypes: Array[AnnotatorType]

    Annotator reference id.

    Annotator reference id. Used to identify elements in metadata or to refer to this annotator type

    Definition Classes
    MLLamaForMultimodalHasInputAnnotationCols
  92. 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
  93. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  94. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  95. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  96. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  97. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  98. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  99. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  100. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  101. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  102. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  103. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  104. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  105. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  106. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  107. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  108. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  109. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  110. val maxImageTiles: IntParam
  111. val maxInputLength: IntParam

    max length of the input sequence (Default: 0)

    max length of the input sequence (Default: 0)

    Definition Classes
    HasGeneratorProperties
  112. val maxOutputLength: IntParam

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

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

    Definition Classes
    HasGeneratorProperties
  113. val merges: MapFeature[(String, String), Int]

    Holding merges.txt coming from RoBERTa model

  114. val minOutputLength: IntParam

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

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

    Definition Classes
    HasGeneratorProperties
  115. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  116. val nReturnSequences: IntParam

    The number of sequences to return from the beam search.

    The number of sequences to return from the beam search.

    Definition Classes
    HasGeneratorProperties
  117. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  118. val noRepeatNgramSize: IntParam

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

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

    Definition Classes
    HasGeneratorProperties
  119. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  120. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  121. val numVisionTokens: IntParam
  122. def onWrite(path: String, spark: SparkSession): Unit
  123. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  124. val outputAnnotatorType: AnnotatorType
  125. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  126. val paddingConstant: IntParam
  127. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  128. var parent: Estimator[MLLamaForMultimodal]
    Definition Classes
    Model
  129. val randomSeed: Option[Long]

    Optional Random seed for the model.

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

    Definition Classes
    HasGeneratorProperties
  130. 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.

    Definition Classes
    HasGeneratorProperties
  131. val resample: IntParam

    An optional resampling filter.

    An optional resampling filter. This can be one of PIL.Image.NEAREST, PIL.Image.BOX, PIL.Image.BILINEAR, PIL.Image.HAMMING, PIL.Image.BICUBIC or PIL.Image.LANCZOS. Only has an effect if do_resize is set to True

    Definition Classes
    HasImageFeatureProperties
  132. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  133. def set[T](feature: StructFeature[T], value: T): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  134. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  135. def set[T](feature: SetFeature[T], value: Set[T]): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  136. def set[T](feature: ArrayFeature[T], value: Array[T]): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  137. final def set(paramPair: ParamPair[_]): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    Params
  138. final def set(param: String, value: Any): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    Params
  139. final def set[T](param: Param[T], value: T): MLLamaForMultimodal.this.type
    Definition Classes
    Params
  140. def setAddedTokens(value: Map[String, Int]): MLLamaForMultimodal.this.type

  141. def setBatchSize(size: Int): MLLamaForMultimodal.this.type

    Size of every batch.

    Size of every batch.

    Definition Classes
    HasBatchedAnnotateImage
  142. def setBeamSize(beamNum: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  143. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  144. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  145. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  146. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  147. final def setDefault(paramPairs: ParamPair[_]*): MLLamaForMultimodal.this.type
    Attributes
    protected
    Definition Classes
    Params
  148. final def setDefault[T](param: Param[T], value: T): MLLamaForMultimodal.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  149. def setDoNormalize(value: Boolean): MLLamaForMultimodal.this.type

    Definition Classes
    HasImageFeatureProperties
  150. def setDoResize(value: Boolean): MLLamaForMultimodal.this.type

    Definition Classes
    HasImageFeatureProperties
  151. def setDoSample(value: Boolean): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  152. def setFeatureExtractorType(value: String): MLLamaForMultimodal.this.type

    Definition Classes
    HasImageFeatureProperties
  153. def setGenerationConfig(value: GenerationConfig): MLLamaForMultimodal.this.type
  154. def setIgnoreTokenIds(tokenIds: Array[Int]): MLLamaForMultimodal.this.type

  155. def setImageMean(value: Array[Double]): MLLamaForMultimodal.this.type

    Definition Classes
    HasImageFeatureProperties
  156. def setImageStd(value: Array[Double]): MLLamaForMultimodal.this.type

    Definition Classes
    HasImageFeatureProperties
  157. def setImageToken(value: Int): MLLamaForMultimodal.this.type

  158. final def setInputCols(value: String*): MLLamaForMultimodal.this.type
    Definition Classes
    HasInputAnnotationCols
  159. def setInputCols(value: Array[String]): MLLamaForMultimodal.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  160. def setLazyAnnotator(value: Boolean): MLLamaForMultimodal.this.type
    Definition Classes
    CanBeLazy
  161. def setMaxImageTiles(value: Int): MLLamaForMultimodal.this.type

  162. def setMaxInputLength(value: Int): MLLamaForMultimodal.this.type
    Definition Classes
    HasGeneratorProperties
  163. def setMaxOutputLength(value: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  164. def setMerges(value: Map[(String, String), Int]): MLLamaForMultimodal.this.type

  165. def setMinOutputLength(value: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  166. def setModelIfNotSet(spark: SparkSession, preprocessor: Preprocessor, onnxWrappers: Option[DecoderWrappers], openvinoWrapper: Option[MLLamaWrappers]): MLLamaForMultimodal.this.type

  167. def setNReturnSequences(beamNum: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  168. def setNoRepeatNgramSize(value: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  169. def setNumVisionTokens(value: Int): MLLamaForMultimodal.this.type

  170. final def setOutputCol(value: String): MLLamaForMultimodal.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  171. def setPaddingConstant(value: Int): MLLamaForMultimodal.this.type

  172. def setParent(parent: Estimator[MLLamaForMultimodal]): MLLamaForMultimodal
    Definition Classes
    Model
  173. def setRandomSeed(value: Int): MLLamaForMultimodal.this.type

  174. def setRandomSeed(value: Long): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  175. def setRepetitionPenalty(value: Double): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  176. def setResample(value: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasImageFeatureProperties
  177. def setSize(value: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasImageFeatureProperties
  178. def setStopTokenIds(value: Array[Int]): MLLamaForMultimodal.this.type

  179. def setTask(value: String): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  180. def setTemperature(value: Double): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  181. def setTopK(value: Int): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  182. def setTopP(value: Double): MLLamaForMultimodal.this.type

    Definition Classes
    HasGeneratorProperties
  183. def setVocabulary(value: Map[String, Int]): MLLamaForMultimodal.this.type

  184. val size: IntParam

    Resize the input to the given size.

    Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an integer is provided, then the input will be resized to (size, size). Only has an effect if do_resize is set to True.

    Definition Classes
    HasImageFeatureProperties
  185. val stopTokenIds: IntArrayParam

    Stop tokens to terminate the generation

    Stop tokens to terminate the generation

    Definition Classes
    MLLamaForMultimodalHasGeneratorProperties
  186. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  187. val task: Param[String]

    Set transformer task, e.g.

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

    Definition Classes
    HasGeneratorProperties
  188. val temperature: DoubleParam

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

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

    Definition Classes
    HasGeneratorProperties
  189. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  190. val topK: IntParam

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

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

    Definition Classes
    HasGeneratorProperties
  191. 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)

    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)

    Definition Classes
    HasGeneratorProperties
  192. 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
  193. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  194. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  195. 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
  196. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  197. val uid: String
    Definition Classes
    MLLamaForMultimodal → Identifiable
  198. 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
  199. val vocabulary: MapFeature[String, Int]

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

  200. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  201. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  202. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  203. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  204. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
  205. def writeOpenvinoModel(path: String, spark: SparkSession, openvinoWrapper: OpenvinoWrapper, suffix: String, fileName: String): Unit
    Definition Classes
    WriteOpenvinoModel
  206. def writeOpenvinoModels(path: String, spark: SparkSession, ovWrappersWithNames: Seq[(OpenvinoWrapper, String)], suffix: String): Unit
    Definition Classes
    WriteOpenvinoModel

Inherited from HasEngine

Inherited from HasGeneratorProperties

Inherited from WriteOpenvinoModel

Inherited from HasImageFeatureProperties

Inherited from CanBeLazy

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[MLLamaForMultimodal]

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