Add LoRA support for fine-tuning

[smandal94]

Is your feature request related to a problem? Please describe. With increasing parameter sizes of pre-trained models, it has become necessary to adapt parameter efficient fine-tuning methods like LoRA, to allow people to work in constrained resource environments.

Describe the solution you'd like Add PEFT library support in configure_models() function for different tasks.

[romeokienzler]

JJ (Johannes Jakubik) -> put in the loop

[romeokienzler]

@smandal94 creating PR (probably WIP)

[paolofraccaro]

@blumenstiel and his student have a working prototype

[smandal94]

235