Feature/phi4 fine tune

[lab176344]

Description

Adding support for fine tuning Phi-4 Multimodal instruct

List any dependencies that are required for this change.

Type of change

Please delete options that are not relevant.

• [ ] Bug fix (non-breaking change which fixes an issue)
• [x] New feature (non-breaking change which adds functionality)
• [x] This change requires a documentation update

How has this change been tested, please provide a testcase or example of how you tested the change?

Testing in progress

Any specific deployment considerations

QLora is not working as the base model is trained with Lora adapters and are merged in the transformer, we might have to monkey patch it or find other way to do it

For example, documentation changes, usability, usage/costs, secrets, etc.

Docs

• [ ] Docs updated? What were the changes: TBD

[CLAassistant]

All committers have signed the CLA.

[fire]

What is required to progress on this?

[lab176344]

I think we have to finish the review and do changes if anything is required but otherwise nothing in my opinion