RAFT fine-tuning technique with Deep Lake Dataloader

[efenocchi]

What does this PR do?

I added the capability to fine-tune an LLM using RAFT, a technique designed to create a dataset that helps the model better distinguish important context from irrelevant information (paper here).

I followed the process used to create the Alpaca dataset and adapted it to my needs. The dataset can be saved in Deep Lake and accessed directly during training.

Fixes # (issue)

Feature/Issue validation/testing

Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

• Test A
  Logs for Test A

I encounter a problem when I try to run tests, even those from the official repository. Running python -m pytest src/tests/ generates the following errors. What am I doing wrong?

• Test B
  Logs for Test B

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

Thanks for contributing 🎉!