[FEA]: Run Fine tuned models in pipeline

Is this a new feature, an improvement, or a change to existing functionality?

Improvement

How would you describe the priority of this feature request

Significant improvement

Please provide a clear description of problem this feature solves

We need to be able to run fine tuned versions of the embedding models that we support.

Describe the feature, and optionally a solution or implementation and any alternatives

We should be able to use a saved Fine tuned model (using the directory path) as part of the pipeline. I.e. User fine tunes the embedding model, they should be able to use that in the pipeline.

Additional context

No response