hohoCode

I think probably it should be something like: > u = dist - expected_quant

I used to run Torch on Windows (like six months ago, but have not tried GPU, only tried windows torch on CPU). I followed all the instructions here: https://github.com/diz-vara/luajit-rocks You...

Unfortunately not yet with NeuralTalk.

@apanimesh061 I did not have those errors (but that was like six months ago). I am not sure if this has anything to do with recent backend THNN updates. I...

The batch size is the No.1 dim; the 4 gates stuff is the No.2 dim. Plus nn.Reshape() supports batch processing. Therefore this is correct.

Great work! One real quick question, have you tried conv-lora on standard text tasks instead of image/SAM tasks? If so, how was it? If havnt tried, do you think it...

> we find that interpolating features to larger scales for local prior injection is more beneficial, given that features in the Vision Transformer (ViT) are downscaled by a factor (e.g.,...

1. Implementing multiple GPU training for AutoMM is an invaluable task. This will be a critical element in facilitating larger model training for AutoGluon's future development, particularly in the direction...

Not sure lots of companies will be willing to switch to uv due to various software management reasons. Maybe it is better to not replace pip, but just to keep...