> Thanks to HUAWEI Ascend NPU Team for supporting us.
They acknowledge they currently don't have enough hardware access to achieve what they want. They are currently training on 8x A100-80G, and the input size is 8 frames * 128 * 128. It takes about a week to train enough to generate ucf-like videos.
I think there's a lot of room in FLOSS AI for "@home" style distributed training incorporating some features of federated learning. The limiting factor at the moment is that large models have a minimum VRAM requirement which is often higher than the 16-24GB that home users would be expected to have.
Your comment doesn't say anything that can be agreed with, refuted, expanded on, or have a dialog around. In what way is PKU-YuanGroup not being open to the a broad community?
5 comments
[ 2.7 ms ] story [ 28.1 ms ] threadThey are definitely active on HN.
Because that's whats its going to take
They acknowledge they currently don't have enough hardware access to achieve what they want. They are currently training on 8x A100-80G, and the input size is 8 frames * 128 * 128. It takes about a week to train enough to generate ucf-like videos.
I think there's a lot of room in FLOSS AI for "@home" style distributed training incorporating some features of federated learning. The limiting factor at the moment is that large models have a minimum VRAM requirement which is often higher than the 16-24GB that home users would be expected to have.