Fanxu Meng

> @fxmeng Let me know once this is ready for another review. Hi, @BenjaminBossan, I have completed all the document writing as your suggestions, and have also provided an example...

> Thanks a lot for the updates. We're making good progress but there are still a couple of steps to take. Please check out my comments. > > ## Conversion...

> > Regarding the conversion from PiSSA to LoRA, it might not be possible to compute (\Delta W) using only the residual model and PiSSA modules during the training process....

> Thanks a lot for the recent changes, these should make the usage of PiSSA more comfortable for the user, good work. > > I left a couple of comments,...

> Thanks for the updates, I don't think we're missing a lot at this point. > > In this review, I did a deep dive into the conversion part so...

> Does this means that as long as I am not using Quantization for finetuning and serving the model, it is alright for me convert the pissa to lora? Yes,...

> Thanks for such a thoughtful, detailed and helpful answer. I am trying it out and seeing very encouraging initial results. Kudos for this fantastic work. > > While trying...

> Thanks for the updates @fxmeng. Could you please also fix the merge conflict and let me know once this is ready for review? Hey @BenjaminBossan, I have added the...

> The test `test_t5_pissa_8bit[cuda]` is failing on when I run it on my machine: > > > AssertionError: assert tensor(0.0288, device='cuda:0', grad_fn=) < (tensor(0.0223, device='cuda:0', grad_fn=) / 1.03) > >...

> The `xfail` marker that you added is in the wrong place (it's not doing anything). What I meant is the following: IIUC, the test `test_lora_pissa_conversion_same_output_after_loading` would fail if we...