Llama2: Multi-lora example notebook, Custom generator

[jambayk]

Describe your changes

• Add a notebook showing an end-to-end example for qlora fine-tuning, model optimization, adapter extraction and deployment with multiple adapters.
• Implemented a custom text generator with can handle multiple lora adapters. Also implemented different types of QV cache management. These are stored under examples/utils and can be reused for other models.

Checklist before requesting a review

• Add unit tests for this change.
• Make sure all tests can pass.
• Update documents if necessary.
• Lint and apply fixes to your code by running lintrunner -a
• Is this a user-facing change? If yes, give a description of this change to be included in the release notes.
• Is this PR including examples changes? If yes, please remember to update example documentation in a follow-up PR.

(Optional) Issue link

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB