If set to true and a compressed_definition is provided,
the request defers definition decompression and skips relevant
validations.
Whether to wait for all child operations (e.g. model download) to complete.
The compressed (GZipped and Base64 encoded) inference definition of the model. If compressed_definition is specified, then definition cannot be specified.
Collection of preprocessors
A human-readable description of the inference trained model.
Inference configuration provided when storing the model config
Specifies the number of top class predictions to return. Defaults to 0.
Specifies the maximum number of feature importance values per document.
Default value is 0.
Specifies the type of the predicted field to write. Acceptable values are: string, number, boolean. When boolean is provided 1.0 is transformed to true and 0.0 to false.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Specifies the field to which the top classes are written. Defaults to top_classes.
Text classification configuration options
Specifies the number of top class predictions to return. Defaults to 0.
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Classification labels to apply other than the stored labels. Must have the same deminsions as the default configured labels
Zero shot classification configuration options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Hypothesis template used when tokenizing labels for prediction
Default value is "This example is {}.".
The zero shot classification labels indicating entailment, neutral, and contradiction Must contain exactly and only entailment, neutral, and contradiction
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Indicates if more than one true label exists.
Default value is false.
The labels to predict.
Fill mask inference options
The string/token which will be removed from incoming documents and replaced with the inference prediction(s). In a response, this field contains the mask token for the specified model/tokenizer. Each model and tokenizer has a predefined mask token which cannot be changed. Thus, it is recommended not to set this value in requests. However, if this field is present in a request, its value must match the predefined value for that model/tokenizer, otherwise the request will fail.
Specifies the number of top class predictions to return. Defaults to 0.
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Named entity recognition options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
The token classification labels. Must be IOB formatted tags
Pass through configuration options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Text embedding inference options
The number of dimensions in the embedding output
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Text expansion inference options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Question answering inference options
Specifies the number of top class predictions to return. Defaults to 0.
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
The maximum answer length to consider
An object map that contains metadata about the model.
Values are tree_ensemble, lang_ident, or pytorch.
The estimated memory usage in bytes to keep the trained model in memory. This property is supported only if defer_definition_decompression is true or the model definition is not supplied.
The platform architecture (if applicable) of the trained mode. If the model
only works on one platform, because it is heavily optimized for a particular
processor architecture and OS combination, then this field specifies which.
The format of the string must match the platform identifiers used by Elasticsearch,
so one of, linux-x86_64, linux-aarch64, darwin-x86_64, darwin-aarch64,
or windows-x86_64. For portable models (those that work independent of processor
architecture or OS features), leave this field unset.
An array of tags to organize the model.
Values are tree_ensemble, lang_ident, or pytorch.
A comma delimited string of tags. A trained model can have many tags, or none.
Information on the creator of the trained model.
Any field map described in the inference configuration takes precedence.
The free-text description of the trained model.
The estimated heap usage in bytes to keep the trained model in memory.
The estimated number of operations to use the trained model.
True if the full model definition is present.
Inference configuration provided when storing the model config
Specifies the number of top class predictions to return. Defaults to 0.
Specifies the maximum number of feature importance values per document.
Default value is 0.
Specifies the type of the predicted field to write. Acceptable values are: string, number, boolean. When boolean is provided 1.0 is transformed to true and 0.0 to false.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Specifies the field to which the top classes are written. Defaults to top_classes.
Text classification configuration options
Specifies the number of top class predictions to return. Defaults to 0.
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Classification labels to apply other than the stored labels. Must have the same deminsions as the default configured labels
Zero shot classification configuration options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Hypothesis template used when tokenizing labels for prediction
Default value is "This example is {}.".
The zero shot classification labels indicating entailment, neutral, and contradiction Must contain exactly and only entailment, neutral, and contradiction
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Indicates if more than one true label exists.
Default value is false.
The labels to predict.
Fill mask inference options
The string/token which will be removed from incoming documents and replaced with the inference prediction(s). In a response, this field contains the mask token for the specified model/tokenizer. Each model and tokenizer has a predefined mask token which cannot be changed. Thus, it is recommended not to set this value in requests. However, if this field is present in a request, its value must match the predefined value for that model/tokenizer, otherwise the request will fail.
Specifies the number of top class predictions to return. Defaults to 0.
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Named entity recognition options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
The token classification labels. Must be IOB formatted tags
Pass through configuration options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Text embedding inference options
The number of dimensions in the embedding output
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Text expansion inference options
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
Question answering inference options
Specifies the number of top class predictions to return. Defaults to 0.
Tokenization options stored in inference configuration
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
BERT and MPNet tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
RoBERTa tokenization configuration options
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
Should the tokenizer prefix input with a space character
Default value is false.
Should the tokenizer lower case the text
Default value is false.
Maximum input sequence length for the model
Default value is 512.
Tokenization spanning options. Special value of -1 indicates no spanning takes place
Default value is -1.
Values are first, second, or none.
Is tokenization completed with special tokens
Default value is true.
The field that is added to incoming documents to contain the inference prediction. Defaults to predicted_value.
The maximum answer length to consider
The license level of the trained model.
An object that contains the baseline for feature importance values. For regression analysis, it is a single value. For classification analysis, there is a value for each class.
List of the available hyperparameters optimized during the fine_parameter_tuning phase as well as specified by the user.
A positive number showing how much the parameter influences the variation of the loss function. For hyperparameters with values that are not specified by the user but tuned during hyperparameter optimization.
A number between 0 and 1 showing the proportion of influence on the variation of the loss function among all tuned hyperparameters. For hyperparameters with values that are not specified by the user but tuned during hyperparameter optimization.
Indicates if the hyperparameter is specified by the user (true) or optimized (false).
The value of the hyperparameter, either optimized or specified by the user.
An array of the total feature importance for each feature used from the training data set. This array of objects is returned if data frame analytics trained the model and the request includes total_feature_importance in the include request parameter.
A collection of feature importance statistics related to the training data set for this particular feature.
The average magnitude of this feature across all the training data. This value is the average of the absolute values of the importance for this feature.
The maximum importance value across all the training data for this feature.
The minimum importance value across all the training data for this feature.
If the trained model is a classification model, feature importance statistics are gathered per target class value.
curl \
--request PUT 'http://api.example.com/_ml/trained_models/{model_id}' \
--header "Authorization: $API_KEY" \
--header "Content-Type: application/json" \
--data '{"compressed_definition":"string","definition":{"preprocessors":[{"frequency_encoding":{"field":"string","feature_name":"string","frequency_map":{"additionalProperty1":42.0,"additionalProperty2":42.0}},"one_hot_encoding":{"field":"string","hot_map":{"additionalProperty1":"string","additionalProperty2":"string"}},"target_mean_encoding":{"field":"string","feature_name":"string","target_map":{"additionalProperty1":42.0,"additionalProperty2":42.0},"default_value":42.0}}],"trained_model":{"tree":{"classification_labels":["string"],"feature_names":["string"],"target_type":"string","tree_structure":[{"decision_type":"string","default_left":true,"leaf_value":42.0,"left_child":42.0,"node_index":42.0,"right_child":42.0,"split_feature":42.0,"split_gain":42.0,"threshold":42.0}]},"tree_node":{"decision_type":"string","default_left":true,"leaf_value":42.0,"left_child":42.0,"node_index":42.0,"right_child":42.0,"split_feature":42.0,"split_gain":42.0,"threshold":42.0},"ensemble":{"aggregate_output":{"logistic_regression":{"weights":42.0},"weighted_sum":{"weights":42.0},"weighted_mode":{"weights":42.0},"exponent":{"weights":42.0}},"classification_labels":["string"],"feature_names":["string"],"target_type":"string","trained_models":[{}]}}},"description":"string","inference_config":{"regression":{"results_field":"string","num_top_feature_importance_values":0},"classification":{"num_top_classes":42.0,"num_top_feature_importance_values":0,"prediction_field_type":"string","results_field":"string","top_classes_results_field":"string"},"text_classification":{"num_top_classes":42.0,"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"results_field":"string","classification_labels":["string"],"vocabulary":{"index":"string"}},"zero_shot_classification":{"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"hypothesis_template":"\"This example is {}.\"","classification_labels":["string"],"results_field":"string","multi_label":false,"labels":["string"]},"fill_mask":{"mask_token":"string","num_top_classes":42.0,"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"results_field":"string","vocabulary":{"index":"string"}},"learning_to_rank":{"default_params":{"additionalProperty1":{},"additionalProperty2":{}},"feature_extractors":[{}],"num_top_feature_importance_values":42.0},"ner":{"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"results_field":"string","classification_labels":["string"],"vocabulary":{"index":"string"}},"pass_through":{"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"results_field":"string","vocabulary":{"index":"string"}},"text_embedding":{"embedding_size":42.0,"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"results_field":"string","vocabulary":{"index":"string"}},"text_expansion":{"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"results_field":"string","vocabulary":{"index":"string"}},"question_answering":{"num_top_classes":42.0,"tokenization":{"bert":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"bert_ja":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"mpnet":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true},"roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true,"add_prefix_space":false},"xlm_roberta":{"do_lower_case":false,"max_sequence_length":512,"span":-1,"truncate":"first","with_special_tokens":true}},"results_field":"string","max_answer_length":42.0}},"input":{"field_names":"string"},"metadata":{},"model_type":"tree_ensemble","model_size_bytes":42.0,"platform_architecture":"string","tags":["string"],"prefix_strings":{"ingest":"string","search":"string"}}'