Fix: Implement LoRA on Custom Model with Transformer Encoder

[cosineai]

This pull request addresses the issue of implementing LoRA on a custom model that includes a transformer encoder from PyTorch. The main challenge was targeting the q, k, and v projection weights in the self-attention block of the transformer encoder layer.

Changes made:

• Modified the LoRALayer class to inherit from nn.Module, which is necessary for integrating LoRA with PyTorch modules.

This change allows for the correct application of LoRA to the specified projection weights, facilitating the desired functionality in the custom model. This should resolve the issue of not being able to find module names corresponding to the q, k, and v projections in the PyTorch transformer encoder.