Enable users to utilize tokens abstraction in the converted tokens to prevent multiple LoRAs collisions.

**Is your feature request related to a problem? Please describe.**
By I guess mostly historical reasons the token is being used for the provided entity, which is fine, unless I load multiple LoRAs that use the same token. How do we distinguish which one entity will get called?

**Describe the solution you'd like.**
I propose we make an experimental flag that will utilize provided token abstractions instead of `s`, for example . In case of mulitple tokens that would be , , ...

Start by tracing how converted tokens currently represent the provided entity as `` and where the experimental option would select token abstractions instead. The work is done when the flag uses the proposed distinct abstractions for multiple LoRAs without collisions, while preserving the existing behavior when disabled.

Vom Indexierungsmodell aus dem Issue-Text verfasst.