ModelName

The name of the model to use. This model name must match exactly the name of a model on Hugging Face.

When you start the server, Answer Server downloads the model from Hugging Face. It then caches it for future use. You can control the location of the cache by setting CacheDirectory.

You can optionally choose the version of the model to use, by setting ModelRevision.

This parameter has an effect only when Type is set to ExtractiveQuestionAnsweringLLM or GenerativeLLM.

Type: String
Default:  
Required: Yes, when Type is set to ExtractiveQuestionAnsweringLLM or GenerativeLLM
Configuration Section: MyLLMModule
Example: ModelName=google/flan-t5-small
See Also: Type
CacheDirectory
ModelRevision