-
Hi! in the recipe, if i do not want to quantize and perform structured pruning, is it okk to give quantize:false like below and do not provide QuantizationModifier in the recipe?
SparseGPTModif…
-
Why did I use llama2-7B when pruningthe model to the same size as the original model
-
Hi, thanks for the great work. I have a question about the experiments in predefined structured pruning methods. I am not sure I am understanding the paper correctly.
For predefined structured prun…
-
Thanks for your work, but when I run this code, there is a error: 'Namespace' object has no attribute 'use_kwta', in utils/continual_model.py", line 244, in structured_pruning.
-
Hi there.
Thank you for your excellent paper.
I have some questions about [Comparing Rewinding and Fine-tuning in Neural Network Pruning](https://openreview.net/forum?id=S1gSj0NKvB). I read intere…
-
Hello, have you updated the code of structured pruning
-
Greetings,
We are the authors of the [said paper](https://openreview.net/pdf?id=LdEhiMG9WLO)/[code](https://github.com/choH/lottery_regulated_grouped_kernel_pruning), and we thank you for your incl…
-
After reading the paper it never made sense that structured pruning was pruning what, parameters, weights? I think it's a bit abstract, please answer my questions, thanks!
-
Hi,
torch.nn.PixelShuffle is change the number of channels, which is not treated well using torch pruning.
For example, I have layer with shape of 1*16*576*1024, and by using PixelShuffle the output…
-
in the paper, you found the unimportant SD block/layer.
In that case, you may not have to retrain the model
(because if you erase unimportant block/layer, the performance is almost preserved)
Can…