nip.language_model_server.types.LmLoraAdapterConfig#

class nip.language_model_server.types.LmLoraAdapterConfig(*, r: int, lora_alpha: int, lora_dropout: float)[source]#

Configuration for a LoRA adapter to be applied on top of a base model.

See Yu et al. [YYK+23] for the original LoRA paper.

Attributes

`__fields_set__`
`model_computed_fields`
`model_config`	Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
`model_extra`	Get extra fields set during validation.
`model_fields`
`model_fields_set`	Returns the set of fields that have been explicitly set on this model instance.
`r`	The rank of the LoRA adapter, controlling the number of trainable parameters.
`lora_alpha`	The scaling factor for the LoRA adapter, for the strength of the adapter.
`lora_dropout`	The dropout rate for the LoRA layers.

Methods

nip.language_model_server.types.LmLoraAdapterConfig