-
I've been observing that for models that take a large amount of steps to reach the early stopping criteria (~20k+ steps), increasing the learning rate significantly (5e-5 --> 2e-4) often cuts the numb…
-
Hi! I have a quick question regarding the future prospects for the package.
A common use case for optimization is to have a dataset that fully contains your set of choices, as opposed to an analyt…
-
### What you would like to be added?
Inspired by this research paper [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://proceedings.mlsys.org/paper_files/paper/2024/file/b74a8de47d…
-
### Checklist
- [ ] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a …
-
I'm trying to compress the ssd_mobilenet_v1_fpn_640x640_coco17_tpu-8 model (from model zoo) with tensorflow optimization tool, or more specifically, tensorflow_model_optimization, which supports quant…
-
hello i found that in your code you save images as '.bmp'. i changed the code to save images as '.jpg' and found minigpt4 said the saved adversarial images are blurred and pixelated, which suggests th…
-
# 🐛 Bug
Analytic acquisition functions like ExpectedImprovement and PosteriorStandardDeviation don't work with SingleTaskVariationalGP when trained on a multi-output dataset. I believe this is bec…
-
Has anyone tried downscaling the K and/or Q matrices for repeated layers in franken-merges? This should act like changing the temperature of the softmax and effectively smooth the distribution:
**H…
-
Very excellent job, if you migrate him to 50-step SD-2-1, can you work well?
-
Hi,
First of all, thank you for sharing this repository; it is really helpful!
I noticed that the runtimes of the ResNet50 BatchEnsemble model are much longer than the ResNet50 deterministic mod…