spark-nlp 5.5.3__py2.py3-none-any.whl → 6.0.0__py2.py3-none-any.whl

sparknlp/annotator/seq2seq/auto_gguf_vision_model.py

@@ -0,0 +1,333 @@
+#  Copyright 2017-2025 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 the AutoGGUFVisionModel."""
+from sparknlp.common import *
+
+
+class AutoGGUFVisionModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
+    """Multimodal annotator that uses the llama.cpp library to generate text completions with large
+    language models. It supports ingesting images for captioning.
+
+    At the moment only CLIP based models are supported.
+
+    For settable parameters, and their explanations, see HasLlamaCppInferenceProperties,
+    HasLlamaCppModelProperties and refer to the llama.cpp documentation of
+    `server.cpp <https://github.com/ggerganov/llama.cpp/tree/7d5e8777ae1d21af99d4f95be10db4870720da91/examples/server>`__
+    for more information.
+
+    If the parameters are not set, the annotator will default to use the parameters provided by
+    the model.
+
+    This annotator expects a column of annotator type AnnotationImage for the image and
+    Annotation for the caption. Note that the image bytes in the image annotation need to be
+    raw image bytes without preprocessing. We provide the helper function
+    ImageAssembler.loadImagesAsBytes to load the image bytes from a directory.
+
+    Pretrained models can be loaded with ``pretrained`` of the companion object:
+
+    .. code-block:: python
+
+        autoGGUFVisionModel = AutoGGUFVisionModel.pretrained() \\
+            .setInputCols(["image", "document"]) \\
+            .setOutputCol("completions")
+
+
+    The default model is ``"llava_v1.5_7b_Q4_0_gguf"``, if no name is provided.
+
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models>`__.
+
+    For extended examples of usage, see the
+    `AutoGGUFVisionModelTest <https://github.com/JohnSnowLabs/spark-nlp/tree/master/src/test/scala/com/johnsnowlabs/nlp/annotators/seq2seq/AutoGGUFVisionModelTest.scala>`__
+    and the
+    `example notebook <https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples/python/llama.cpp/llama.cpp_in_Spark_NLP_AutoGGUFVisionModel.ipynb>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``IMAGE, DOCUMENT``    ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    nThreads
+        Set the number of threads to use during generation
+    nThreadsDraft
+        Set the number of threads to use during draft generation
+    nThreadsBatch
+        Set the number of threads to use during batch and prompt processing
+    nThreadsBatchDraft
+        Set the number of threads to use during batch and prompt processing
+    nCtx
+        Set the size of the prompt context
+    nBatch
+        Set the logical batch size for prompt processing (must be >=32 to use BLAS)
+    nUbatch
+        Set the physical batch size for prompt processing (must be >=32 to use BLAS)
+    nDraft
+        Set the number of tokens to draft for speculative decoding
+    nChunks
+        Set the maximal number of chunks to process
+    nSequences
+        Set the number of sequences to decode
+    pSplit
+        Set the speculative decoding split probability
+    nGpuLayers
+        Set the number of layers to store in VRAM (-1 - use default)
+    nGpuLayersDraft
+        Set the number of layers to store in VRAM for the draft model (-1 - use default)
+    gpuSplitMode
+        Set how to split the model across GPUs
+    mainGpu
+        Set the main GPU that is used for scratch and small tensors.
+    tensorSplit
+        Set how split tensors should be distributed across GPUs
+    grpAttnN
+        Set the group-attention factor
+    grpAttnW
+        Set the group-attention width
+    ropeFreqBase
+        Set the RoPE base frequency, used by NTK-aware scaling
+    ropeFreqScale
+        Set the RoPE frequency scaling factor, expands context by a factor of 1/N
+    yarnExtFactor
+        Set the YaRN extrapolation mix factor
+    yarnAttnFactor
+        Set the YaRN scale sqrt(t) or attention magnitude
+    yarnBetaFast
+        Set the YaRN low correction dim or beta
+    yarnBetaSlow
+        Set the YaRN high correction dim or alpha
+    yarnOrigCtx
+        Set the YaRN original context size of model
+    defragmentationThreshold
+        Set the KV cache defragmentation threshold
+    numaStrategy
+        Set optimization strategies that help on some NUMA systems (if available)
+    ropeScalingType
+        Set the RoPE frequency scaling method, defaults to linear unless specified by the model
+    poolingType
+        Set the pooling type for embeddings, use model default if unspecified
+    modelDraft
+        Set the draft model for speculative decoding
+    modelAlias
+        Set a model alias
+    lookupCacheStaticFilePath
+        Set path to static lookup cache to use for lookup decoding (not updated by generation)
+    lookupCacheDynamicFilePath
+        Set path to dynamic lookup cache to use for lookup decoding (updated by generation)
+    embedding
+        Whether to load model with embedding support
+    flashAttention
+        Whether to enable Flash Attention
+    inputPrefixBos
+        Whether to add prefix BOS to user inputs, preceding the `--in-prefix` string
+    useMmap
+        Whether to use memory-map model (faster load but may increase pageouts if not using mlock)
+    useMlock
+        Whether to force the system to keep model in RAM rather than swapping or compressing
+    noKvOffload
+        Whether to disable KV offload
+    systemPrompt
+        Set a system prompt to use
+    chatTemplate
+        The chat template to use
+    inputPrefix
+        Set the prompt to start generation with
+    inputSuffix
+        Set a suffix for infilling
+    cachePrompt
+        Whether to remember the prompt to avoid reprocessing it
+    nPredict
+        Set the number of tokens to predict
+    topK
+        Set top-k sampling
+    topP
+        Set top-p sampling
+    minP
+        Set min-p sampling
+    tfsZ
+        Set tail free sampling, parameter z
+    typicalP
+        Set locally typical sampling, parameter p
+    temperature
+        Set the temperature
+    dynatempRange
+        Set the dynamic temperature range
+    dynatempExponent
+        Set the dynamic temperature exponent
+    repeatLastN
+        Set the last n tokens to consider for penalties
+    repeatPenalty
+        Set the penalty of repeated sequences of tokens
+    frequencyPenalty
+        Set the repetition alpha frequency penalty
+    presencePenalty
+        Set the repetition alpha presence penalty
+    miroStat
+        Set MiroStat sampling strategies.
+    mirostatTau
+        Set the MiroStat target entropy, parameter tau
+    mirostatEta
+        Set the MiroStat learning rate, parameter eta
+    penalizeNl
+        Whether to penalize newline tokens
+    nKeep
+        Set the number of tokens to keep from the initial prompt
+    seed
+        Set the RNG seed
+    nProbs
+        Set the amount top tokens probabilities to output if greater than 0.
+    minKeep
+        Set the amount of tokens the samplers should return at least (0 = disabled)
+    grammar
+        Set BNF-like grammar to constrain generations
+    penaltyPrompt
+        Override which part of the prompt is penalized for repetition.
+    ignoreEos
+        Set whether to ignore end of stream token and continue generating (implies --logit-bias 2-inf)
+    disableTokenIds
+        Set the token ids to disable in the completion
+    stopStrings
+        Set strings upon seeing which token generation is stopped
+    samplers
+        Set which samplers to use for token generation in the given order
+    useChatTemplate
+        Set whether or not generate should apply a chat template
+
+    Notes
+    -----
+    To use GPU inference with this annotator, make sure to use the Spark NLP GPU package and set
+    the number of GPU layers with the `setNGpuLayers` method.
+
+    When using larger models, we recommend adjusting GPU usage with `setNCtx` and `setNGpuLayers`
+    according to your hardware to avoid out-of-memory errors.
+
+    Examples
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> from pyspark.sql.functions import lit
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("caption") \\
+    ...     .setOutputCol("caption_document")
+    >>> imageAssembler = ImageAssembler() \\
+    ...     .setInputCol("image") \\
+    ...     .setOutputCol("image_assembler")
+    >>> imagesPath = "src/test/resources/image/"
+    >>> data = ImageAssembler \\
+    ...     .loadImagesAsBytes(spark, imagesPath) \\
+    ...     .withColumn("caption", lit("Caption this image.")) # Add a caption to each image.
+    >>> nPredict = 40
+    >>> model = AutoGGUFVisionModel.pretrained() \\
+    ...     .setInputCols(["caption_document", "image_assembler"]) \\
+    ...     .setOutputCol("completions") \\
+    ...     .setBatchSize(4) \\
+    ...     .setNGpuLayers(99) \\
+    ...     .setNCtx(4096) \\
+    ...     .setMinKeep(0) \\
+    ...     .setMinP(0.05) \\
+    ...     .setNPredict(nPredict) \\
+    ...     .setNProbs(0) \\
+    ...     .setPenalizeNl(False) \\
+    ...     .setRepeatLastN(256) \\
+    ...     .setRepeatPenalty(1.18) \\
+    ...     .setStopStrings(["</s>", "Llama:", "User:"]) \\
+    ...     .setTemperature(0.05) \\
+    ...     .setTfsZ(1) \\
+    ...     .setTypicalP(1) \\
+    ...     .setTopK(40) \\
+    ...     .setTopP(0.95)
+    >>> pipeline = Pipeline().setStages([documentAssembler, imageAssembler, model])
+    >>> pipeline.fit(data).transform(data) \\
+    ...     .selectExpr("reverse(split(image.origin, '/'))[0] as image_name", "completions.result") \\
+    ...     .show(truncate = False)
+    +-----------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+    |image_name       |result                                                                                                                                                                                        |
+    +-----------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+    |palace.JPEG      |[ The image depicts a large, ornate room with high ceilings and beautifully decorated walls. There are several chairs placed throughout the space, some of which have cushions]               |
+    |egyptian_cat.jpeg|[ The image features two cats lying on a pink surface, possibly a bed or sofa. One cat is positioned towards the left side of the scene and appears to be sleeping while holding]             |
+    |hippopotamus.JPEG|[ A large brown hippo is swimming in a body of water, possibly an aquarium. The hippo appears to be enjoying its time in the water and seems relaxed as it floats]                            |
+    |hen.JPEG         |[ The image features a large chicken standing next to several baby chickens. In total, there are five birds in the scene: one adult and four young ones. They appear to be gathered together] |
+    |ostrich.JPEG     |[ The image features a large, long-necked bird standing in the grass. It appears to be an ostrich or similar species with its head held high and looking around. In addition to]              |
+    |junco.JPEG       |[ A small bird with a black head and white chest is standing on the snow. It appears to be looking at something, possibly food or another animal in its vicinity. The scene takes place out]  |
+    |bluetick.jpg     |[ A dog with a red collar is sitting on the floor, looking at something. The dog appears to be staring into the distance or focusing its attention on an object in front of it.]              |
+    |chihuahua.jpg    |[ A small brown dog wearing a sweater is sitting on the floor. The dog appears to be looking at something, possibly its owner or another animal in the room. It seems comfortable and relaxed]|
+    |tractor.JPEG     |[ A man is sitting in the driver's seat of a green tractor, which has yellow wheels and tires. The tractor appears to be parked on top of an empty field with]                                |
+    |ox.JPEG          |[ A large bull with horns is standing in a grassy field.]                                                                                                                                     |
+    +-----------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------
+    """
+
+    name = "AutoGGUFVisionModel"
+    inputAnnotatorTypes = [AnnotatorType.IMAGE, AnnotatorType.DOCUMENT]
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.seq2seq.AutoGGUFVisionModel", java_model=None):
+        super(AutoGGUFVisionModel, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+
+        self._setDefault(
+            useChatTemplate=True,
+            nCtx=4096,
+            nBatch=512,
+            embedding=False,
+            nPredict=100
+        )
+
+    @staticmethod
+    def loadSavedModel(modelPath, mmprojPath, spark_session):
+        """Loads a locally saved modelPath.
+
+        Parameters
+        ----------
+        modelPath : str
+            Path to the modelPath file
+        mmprojPath : str
+            Path to the mmprojPath file
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        AutoGGUFVisionModel
+            The restored modelPath
+        """
+        from sparknlp.internal import _AutoGGUFVisionLoader
+        jModel = _AutoGGUFVisionLoader(modelPath, mmprojPath, spark_session._jsparkSession)._java_obj
+        return AutoGGUFVisionModel(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="llava_v1.5_7b_Q4_0_gguf", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "llava_v1.5_7b_Q4_0_gguf"
+        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
+        -------
+        AutoGGUFVisionModel
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(AutoGGUFVisionModel, name, lang, remote_loc)

sparknlp/annotator/seq2seq/cohere_transformer.py

@@ -0,0 +1,357 @@
+#  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 the CoHereTransformer."""
+
+from sparknlp.common import *
+
+
+class CoHereTransformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
+    """Cohere: Command-R Transformer
+    
+        C4AI Command-R is a research release of a 35 billion parameter highly performant generative model.
+        Command-R is a large language model with open weights optimized for a variety of use cases including reasoning,
+        summarization, and question answering. Command-R has the capability for multilingual generation evaluated
+        in 10 languages and highly performant RAG capabilities.
+
+        Pretrained models can be loaded with :meth:`.pretrained` of the companion
+        object:
+    
+        >>> CoHere = CoHereTransformer.pretrained() \\
+        ...     .setInputCols(["document"]) \\
+        ...     .setOutputCol("generation")
+    
+    
+        The default model is ``"c4ai_command_r_v01_int4"``, if no name is provided. For available
+        pretrained models please see the `Models Hub
+        <https://sparknlp.org/models?q=CoHere>`__.
+    
+        ====================== ======================
+        Input Annotation types Output Annotation type
+        ====================== ======================
+        ``DOCUMENT``           ``DOCUMENT``
+        ====================== ======================
+    
+        Parameters
+        ----------
+        configProtoBytes
+            ConfigProto from tensorflow, serialized into byte array.
+        minOutputLength
+            Minimum length of the sequence to be generated, by default 0
+        maxOutputLength
+            Maximum length of output text, by default 60
+        doSample
+            Whether or not to use sampling; use greedy decoding otherwise, by default False
+        temperature
+            The value used to modulate the next token probabilities, by default 1.0
+        topK
+            The number of highest probability vocabulary tokens to keep for
+            top-k-filtering, by default 40
+        topP
+            Top cumulative probability for vocabulary tokens, by default 1.0
+    
+            If set to float < 1, only the most probable tokens with probabilities
+            that add up to ``topP`` or higher are kept for generation.
+        repetitionPenalty
+            The parameter for repetition penalty, 1.0 means no penalty. , by default
+            1.0
+        noRepeatNgramSize
+            If set to int > 0, all ngrams of that size can only occur once, by
+            default 0
+        ignoreTokenIds
+            A list of token ids which are ignored in the decoder's output, by
+            default []
+    
+        Notes
+        -----
+        This is a very computationally expensive module, especially on larger
+        sequences. The use of an accelerator such as GPU is recommended.
+    
+        References
+        ----------
+        - `Cohere <https://cohere.for.ai/>`__
+
+    
+        Examples
+        --------
+        >>> import sparknlp
+        >>> from sparknlp.base import *
+        >>> from sparknlp.annotator import *
+        >>> from pyspark.ml import Pipeline
+        >>> documentAssembler = DocumentAssembler() \\
+        ...     .setInputCol("text") \\
+        ...     .setOutputCol("documents")
+        >>> CoHere = CoHereTransformer.pretrained("c4ai_command_r_v01_int4","en") \\
+        ...     .setInputCols(["documents"]) \\
+        ...     .setMaxOutputLength(60) \\
+        ...     .setOutputCol("generation")
+        >>> pipeline = Pipeline().setStages([documentAssembler, CoHere])
+        >>> data = spark.createDataFrame([
+        ...     (
+        ...         1,
+        ...         "<BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>"
+        ...         )
+        ... ]).toDF("id", "text")
+        >>> result = pipeline.fit(data).transform(data)
+        >>> result.select("generation.result").show(truncate=False)
+        +------------------------------------------------+
+        |result                                          |
+        +------------------------------------------------+
+        |[Hello! I'm doing well, thank you for asking! I'm excited to help you with whatever questions you have today. How can I assist you?]|
+        +------------------------------------------------+
+    """
+
+    name = "CoHereTransformer"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    minOutputLength = Param(Params._dummy(), "minOutputLength", "Minimum length of the sequence to be generated",
+                            typeConverter=TypeConverters.toInt)
+
+    maxOutputLength = Param(Params._dummy(), "maxOutputLength", "Maximum length of output text",
+                            typeConverter=TypeConverters.toInt)
+
+    doSample = Param(Params._dummy(), "doSample", "Whether or not to use sampling; use greedy decoding otherwise",
+                     typeConverter=TypeConverters.toBoolean)
+
+    temperature = Param(Params._dummy(), "temperature", "The value used to module the next token probabilities",
+                        typeConverter=TypeConverters.toFloat)
+
+    topK = Param(Params._dummy(), "topK",
+                 "The number of highest probability vocabulary tokens to keep for top-k-filtering",
+                 typeConverter=TypeConverters.toInt)
+
+    topP = Param(Params._dummy(), "topP",
+                 "If set to float < 1, only the most probable tokens with probabilities that add up to ``top_p`` or higher are kept for generation",
+                 typeConverter=TypeConverters.toFloat)
+
+    repetitionPenalty = Param(Params._dummy(), "repetitionPenalty",
+                              "The parameter for repetition penalty. 1.0 means no penalty. See `this paper <https://arxiv.org/pdf/1909.05858.pdf>`__ for more details",
+                              typeConverter=TypeConverters.toFloat)
+
+    noRepeatNgramSize = Param(Params._dummy(), "noRepeatNgramSize",
+                              "If set to int > 0, all ngrams of that size can only occur once",
+                              typeConverter=TypeConverters.toInt)
+
+    ignoreTokenIds = Param(Params._dummy(), "ignoreTokenIds",
+                           "A list of token ids which are ignored in the decoder's output",
+                           typeConverter=TypeConverters.toListInt)
+
+    beamSize = Param(Params._dummy(), "beamSize",
+                     "The number of beams to use for beam search",
+                     typeConverter=TypeConverters.toInt)
+
+    stopTokenIds = Param(Params._dummy(), "stopTokenIds",
+                         "A list of token ids which are considered as stop tokens in the decoder's output",
+                         typeConverter=TypeConverters.toListInt)
+
+    def setIgnoreTokenIds(self, value):
+        """A list of token ids which are ignored in the decoder's output.
+
+        Parameters
+        ----------
+        value : List[int]
+            The words to be filtered out
+        """
+        return self._set(ignoreTokenIds=value)
+
+    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 setMinOutputLength(self, value):
+        """Sets minimum length of the sequence to be generated.
+
+        Parameters
+        ----------
+        value : int
+            Minimum length of the sequence to be generated
+        """
+        return self._set(minOutputLength=value)
+
+    def setMaxOutputLength(self, value):
+        """Sets maximum length of output text.
+
+        Parameters
+        ----------
+        value : int
+            Maximum length of output text
+        """
+        return self._set(maxOutputLength=value)
+
+    def setDoSample(self, value):
+        """Sets whether or not to use sampling, use greedy decoding otherwise.
+
+        Parameters
+        ----------
+        value : bool
+            Whether or not to use sampling; use greedy decoding otherwise
+        """
+        return self._set(doSample=value)
+
+    def setTemperature(self, value):
+        """Sets the value used to module the next token probabilities.
+
+        Parameters
+        ----------
+        value : float
+            The value used to module the next token probabilities
+        """
+        return self._set(temperature=value)
+
+    def setTopK(self, value):
+        """Sets the number of highest probability vocabulary tokens to keep for
+        top-k-filtering.
+
+        Parameters
+        ----------
+        value : int
+            Number of highest probability vocabulary tokens to keep
+        """
+        return self._set(topK=value)
+
+    def setTopP(self, value):
+        """Sets the top cumulative probability for vocabulary tokens.
+
+        If set to float < 1, only the most probable tokens with probabilities
+        that add up to ``topP`` or higher are kept for generation.
+
+        Parameters
+        ----------
+        value : float
+            Cumulative probability for vocabulary tokens
+        """
+        return self._set(topP=value)
+
+    def setRepetitionPenalty(self, value):
+        """Sets the parameter for repetition penalty. 1.0 means no penalty.
+
+        Parameters
+        ----------
+        value : float
+            The repetition penalty
+
+        References
+        ----------
+        See `Ctrl: A Conditional Transformer Language Model For Controllable
+        Generation <https://arxiv.org/pdf/1909.05858.pdf>`__ for more details.
+        """
+        return self._set(repetitionPenalty=value)
+
+    def setNoRepeatNgramSize(self, value):
+        """Sets size of n-grams that can only occur once.
+
+        If set to int > 0, all ngrams of that size can only occur once.
+
+        Parameters
+        ----------
+        value : int
+            N-gram size can only occur once
+        """
+        return self._set(noRepeatNgramSize=value)
+
+    def setBeamSize(self, value):
+        """Sets the number of beams to use for beam search.
+
+        Parameters
+        ----------
+        value : int
+            The number of beams to use for beam search
+        """
+        return self._set(beamSize=value)
+
+    def setStopTokenIds(self, value):
+        """Sets a list of token ids which are considered as stop tokens in the decoder's output.
+
+        Parameters
+        ----------
+        value : List[int]
+            The words to be considered as stop tokens
+        """
+        return self._set(stopTokenIds=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.seq2seq.CoHereTransformer", java_model=None):
+        super(CoHereTransformer, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            minOutputLength=0,
+            maxOutputLength=20,
+            doSample=False,
+            temperature=0.6,
+            topK=-1,
+            topP=0.9,
+            repetitionPenalty=1.0,
+            noRepeatNgramSize=3,
+            ignoreTokenIds=[],
+            batchSize=1,
+            beamSize=1,
+            stopTokenIds=[128001, ]
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session, use_openvino=False):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        CoHereTransformer
+            The restored model
+        """
+        from sparknlp.internal import _CoHereLoader
+        jModel = _CoHereLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
+        return CoHereTransformer(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="c4ai_command_r_v01_int4", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "c4ai_command_r_v01_int4"
+        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
+        -------
+        CoHereTransformer
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(CoHereTransformer, name, lang, remote_loc)