-
I want to follow up regarding our previous discussion at the stable_baslines3 contrib repo, I hope this could serve as the right place, if not please feel free to close this and we continue the discus…
-
### Expected Behavior
flux+cn+lora, when ksamper it OOM
sys info
Total VRAM 24253 MB, total RAM 773393 MB
pytorch version: 2.1.2+cu121
xformers version: 0.0.23.post1
Set vram state to: HIGH_…
-
Hello,
maybe I'm missing it, but is there the 'transform' function, i.e. after you trained the UMAP instance with data you can apply the same instance on an unseen point?
If not, why? And is it fo…
-
Zakres:
- [ ] estymacja parametrów
- [x] analiza danych historycznych - na podstawie wprowadzonych okresów (srednia ann, std ann, skew, kurtosis, max dropdown, normality test)
- [ ] estymacja p…
msz13 updated
5 months ago
-
It may be useful to be able to add a new function to a `BlockFunction`.
Requires `append`. It may be useful to override `__add__` method?
Similarly for `BlockOperator`
-
**tl;dr**: We should let the submission know if an evaluation is going to happen at the current step or not.
## Description
Currently, there is no easy way for the submission to know if the model …
-
We thank the NeuroImage for the opportunity to revise our paper, and the Handling Editor, the editorial team, and three referees for their thoughtful comments and suggestions. We have revised our manu…
-
make_functional + our transforms have worked for most of our users out there. We should evaluate the combination on the torchbenchmark suite of models to see if there are any gaps.
-
### Before
```python
with pm.Model():
...
approx = pm.fit(method='advi')
```
### After
```python
with pm.Model():
...
approx = pm.fit(method='dadvi')
```
### Context …
-
The Jupyter notebook uses `make_graph` with the implicit `counts=True`. The published plot looks something like this:
![image](https://user-images.githubusercontent.com/78827/50282941-770f0280-04a8-1…