-
RE: RE:
Sorry. This turns out to be a effect of the card settings.
This entire behavior is the result of turning on vsync to half adaptive on the card in both cases. By which the card overrides monog…
-
hello guys, i have an issue running the kohya, please someone give me a solution for this, thank you
this is the error message:
![Screenshot 2024-03-31 063842](https://github.com/kohya-ss/sd-scr…
-
**Hi, I'm trying to test training a dreambooth LoRA for SD1.5 faster on 4 GPUs as compared to 1 GPU. Would love any and all help!**
I'm using code from the commit https://github.com/agarwalml/kohy…
-
@karlnapf
The existing EP inference is not scalable.
This issue is about refactoring existing EP inference in Shogun and extend it to [EP inference under FITC approximation](http://www.gaussianproces…
-
*Extracted from a Stable Diffusion oriented guide, but the efficiency of the optimizer applies equally to different networks and architectures.*
There are two types: adaptative and non-adaptative. …
-
Hi Alasdair,
It seems that you are using an adaptive embedding method defined in adaptive.py. I am wondering why not use roberta embedding method since you are using roberta as the encoder. Thanks.…
-
I am noticing that the training just stalls/stops at a certain epoch for some reason. No errors/explanation. Screenshot below. It got stuck at this epoch and has been here for the last 2 hours. I am n…
-
In PyMC3, stein variational gradient is already implemented, but it has to be tested how well it works/how biased it is for small number of particles. In addition, the optimal type of optimizer and le…
-
This would be data that is decomposed into report and reference dates. Current functionality would then be a special case of this.
It would need.
- [ ] An additional delay spline in the model…
-
## ❓ Questions and Help
#### I'm trying to fine-tune BART model for classification task on another language by following the steps in the [example](https://github.com/pytorch/fairseq/blob/master/…