NikhilNayak-debug

Thanks so much @githubnemo these are great suggestions, really appreciate the detailed feedback. We will go ahead and make the changes as you outlined. A couple of points to clarify...

Hello @githubnemo, Thanks again for the helpful feedback and suggestions. We have made the changes you recommended and opened the PR here: [PR Link](https://github.com/huggingface/peft/pull/2685) This includes: * Moving the implementation...

Hello @githubnemo , thank you again for your guidance so far. The current PR ensures that the core OSFT functionality works and follows a unified implementation structure consistent with other...

> This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread....

@githubnemo I have added the continual learning example as requested. Could you please review this PR? The example demonstrates OSF on 3 sequential tasks (ScienceQA, NumGLUE, FOMC) with progressive rank...

> I ran the example with Llama-3.2 1B and got these results. I'm not sure if that's expected, the effective rank is probably smaller since there's probably a difference in...

@githubnemo the PR is ready for review!

> This is actually what got me wondering. I expected the same but in both cases the "average forgetting" numbers were worse for OFT and better for Full FT. Am...