Fanxu Meng

> > 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...

> 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) > >...

> When I run your test above, the values I get the same or very similar values, except for T5 + 8bit: > > ``` > (tensor(0.1253, device='cuda:0'), tensor(0.0223, device='cuda:0'),...

After computing the gradients using loss.backward() method, we can update the parameters of the model using these gradients. However, some stripes may not be crucial to the model's performance, and...

> Thanks for your reply! I guess I know the main idea of your great work, and I just wonder **_When_** to update important parameters. > > I mean, is...