Shaochen (Henry) Zhong comments

Results 7 comments of


                                            Shaochen (Henry) Zhong

VISION of this project.

Adjust goal from drafting a `VISION.md` file to add some lines in `README.md` as current research cannot support a standalone file.

VISION of this project.

Adjust goal from add some lines in `README.md` to mention this issue within `README.md` — as this issue can be fairly dynamic if someone would test out these possible solutions.

Problem when LD_LIBRARY_PATH is required to run python

I needed to clone a venv on a cluster as well, and this saved the day. A big thank you from 9 years later :)

How do you process oasst1 to get 9209 examples

https://huggingface.co/datasets/timdettmers/openassistant-guanaco This should be the one they are using as oasst1. Looks like there are 9,846 samples.

New pruning type for our ICLR22 paper: Grouped Kernel Pruning — a densely structured pruning granularity with better pruning freedom than filter/channel methods.

@he-y As far as we know, Grouped Kernel (within the realm of structured pruning) is a pretty novel pruning granularity, and there is no previous adaptation of GKP within the...

New pruning type for our ICLR22 paper: Grouped Kernel Pruning — a densely structured pruning granularity with better pruning freedom than filter/channel methods.

On the note of giving people a better view, we happened to have this pruning granularity illustration made for rebuttal purposes. We can generalize it on GKP and add a...

New pruning type for our ICLR22 paper: Grouped Kernel Pruning — a densely structured pruning granularity with better pruning freedom than filter/channel methods.

@he-y Thank you, that's fair enough. I have updated my issue title to provide more information, and I will certainly reach out should there be more methods following the GKP...