TokenizerPath

The path to the exported tokenizer file to use. This parameter applies when Type is set to ExtractiveQuestionAnsweringLLM or GenerativeLLM.

You can generate an appropriate tokenizer file to use by using the export_transformers_model.py script, which is provided in your Answer Server installation (see ModelPath).

Type: String
Default:  
Required: Yes, when Type is set to ExtractiveQuestionAnsweringLLM or GenerativeLLM
Configuration Section: MyLLMModule
Example: TokenizerPath=C:\Models\tokenizer.spiece.model
See Also: ModelPath