Add support for LoRA in prompt tuning module (Investigate)

[gkumbhat]

Is your feature request related to a problem? Please describe.

Currently we only support vanilla prompt tuning and multi-task prompt tuning from PEFT library. LoRA has shown to give good performance on variety of datasets. This story is to investigate support for LoRA into the module.

[chakrn]

Should this be added to the 'Add Support for LoRA' milestone? cc: @rawkintrevo

[ibm-peach-fish]

@chakrn / @gkumbhat I think we can close this as "no" i did the second iteration of adding LoRA in Prompt Tuning and it was pushed back.

[chakrn]

cc: @Ssukriti

[Ssukriti]

doing this in steps, but first PR ready for review #270 @gkumbhat