-
Hi. I am using exactly the same code as yours in run_sft.sh:
```
#!/bin/bash
CUR_DIR=`pwd`
ROOT=${CUR_DIR}
export PYTHONPATH=${ROOT}:${PYTHONPATH}
VISION_MODEL=openai/clip-vit-large-pa…
-
### 論文へのリンク
[[arXiv:2004.11362] Supervised Contrastive Learning](https://arxiv.org/abs/2004.11362)
### 著者・所属機関
Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip I…
-
As noted in #54, a switch to an in-place gradient calculation could speed up performance by avoiding array allocations:
> But if in the long run you consider switching to a unified in-place _criter…
p-gw updated
6 months ago
-
I am wondering if the 'tangent-space backpropagation' implemented here in "jaxlie.manifold.value_and_grad" is the same as that defined in the paper "Tangent Space Backpropagation for 3D Transformation…
-
In this issue you can either:
- **Add papers** that you think are interesting to read and discuss (please stick to the format).
- **vote**: should be done using :+1: on comments
-
Adele: Reviews are in! All very positive and constructive, but quite lengthy and a number of extra figures requested.
### Editor:
Thank you for this interesting and well-written contribution. We …
-
### Problem
When adding references to examples it is a bit of hassle to open all the files in order to determine which files don't have the references. So I listed them all using this bash comm…
-
I've tried .25 and .5 augmentation probability, but just outputs blobs after several hours of training. I'm also using 128 image size and 1 attention layer. Any advice?
-
I was going to use the [SD3 weight map](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers/commit/b1148b4028b9ec56ebd36444c193d56aeff7ab56) and try to get this extension to work wi…
-
As observed in #942, QUDA and MILC computed values of the topological charge Q are inconsistent.
MILC's F_munu code is here:
Make Field Strength Tensor,
https://github.com/milc-qcd/milc_qcd/blob/…