githubnemo
githubnemo
Thanks for the PR but I don't think this will pass the tests. Please make sure to run the tests locally and arrange the changes accordingly :) See [this section...
*not stale*
I think I've addressed all review comments. Note that I've removed the predefined targets for ACT since I don't think that it makes sense to provide defaults for a policy...
> I'm interested in using lora to fine-tune, so I'm trying this out. the first thing I hit was that peft doesn't seem to be installed as a dependency when...
Hi @yipingji Sorry for being unclear. I tried highlighting the issue in https://github.com/huggingface/peft/pull/2457#discussion_r2020957043. The `kwargs` come from the `update_layer` calls, the `update_layer` calls get their parameters from the layer `__init__`...
@yipingji gentle ping :)
@yipingji I've reopened the PR and added the WIP tag so stale bot will not bother us.
Hey @yipingji, do you still plan on implementing this further?
Hey @NikhilNayak-debug, thanks for the suggestion and willingness to implement adaptive SVD for PEFT. I skimmed the paper and your draft PR and I think that this would make a...
> Thanks so much [@githubnemo](https://github.com/githubnemo) these are great suggestions, really appreciate the detailed feedback. We will go ahead and make the changes as you outlined. > > A couple of...