ONNXClassification Syntax Elements | Vantage BYOM - ONNXClassification Syntax Elements - Teradata Vantage

Teradata Vantage™ - Bring Your Own Model User Guide
Deployment
VantageCloud
VantageCore
Edition
VMware
Enterprise
IntelliFlex
Lake
Product
Teradata Vantage
Release Number
7.0
Published
October 2025
ft:locale
en-US
ft:lastEdition
2025-11-07
dita:mapPath
fee1607120608274.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
fee1607120608274
Accumulate
Specify one or more column names to add to the output table. Use an asterisk to specify all columns.
An accumulate_column cannot specify column Ids as integers, ranges, or allow the data type BLOB or CLOB.
ModelOutputFieldsMap
Use to map output tensors.
Valid entry: A list of one or more strings.
OutputFormat
List output format values that match the ModelOutputFieldsMap length to provide database formats.
EncodeMaxLength
[Optional] Set the maximum length of the tokenizer encode output tokens.
Default value: 512
Valid values: 1–131072
ShowModelProperties
[Optional] Display the input and output tensor properties of the ONNX model. When set to true, the parameter displays the current model properties rather than run scoring.
Default value: false
OverwriteCachedModel
[Optional] Valid values are: 'current_cached_model', '*', 'true', 't', 'yes', '1', 'false', 'f', 'no', 'n', or '0'. All of these values are equivalent as this argument applies only to the model specified in the model ON clause, which is assumed to be in the cache.
Important: Do not use the OverwriteCachedModel argument except when you are trying to replace a previously cached model. This applies to all models supported by BYOM. Using the argument in other cases, including in concurrent queries or multiple times within a short period of time, may lead to an OOM error from garbage collection not being fast enough.
If a model loaded into the memory of the node fits in the cache, it stays in the cache until being evicted to make space for another model that needs to be loaded or after 7 days if not used. Therefore, a model can remain in the cache after the query that loaded it completes. Other queries that use the same model can use it, saving the cost of reloading it into memory.
You want to overwrite a cached model only when it has been updated, to make sure that the Predict function uses the updated model instead of the cached model.
Default behavior: The function does not overwrite cached models.
UseCache
[Optional] When true, this statement loads the model from the cache.
When false, the model is loaded from the temporary tables for the duration of the query.
String enclosed in single quotes 'false' or 'true'.
Default: False
IsDebug
[Optional] When true, debug statements are added to a trace table that must be created beforehand. See Error Logs.

Only available with BYOM version 3.00.00.02 and later.

Default: False
EnableMemoryCheck
[Optional] When true, enables the memory check for large models to verify there is enough native memory.
String enclosed in single quotes 'false' or 'true'.
Default: True
SkipSpecialTokens
[Optional] When true, skip special tokens in output.
If false, provide special tokens in output.
Default value: true
Const_NAME
[Optional] Allow constant values to be added for use in the model input.