-
# Redesigning the InstructLab Training Repository
We aim to redesign the InstructLab training repository with a focus on simplicity, modularity, and performance. The goal is to create a standalone,…
-
Currently Faster-Whisper only allows you to specify a single language or attempt to detect the language out of a pool of 94 languages. I would like to be able to limit what languages can be detected. …
-
what i think is using this TDDIP methods for simulated sampling pattern (possible not for clinical application), such as the pseudo-radial sampling (Cartesian version of radom radial sampling) as in k…
-
Hi, I write the following sampling code and test the official var_d30.pth ckpt. (I calculate FID/IS using OPENAI's official code)
I find at cfg=1. We have FID=2.31 and IS=62. At cfg=2 the FID=2.0 …
-
There are new methods in scipy for doing sampling of statistical distributions. See the guide at https://docs.scipy.org/doc/scipy/tutorial/stats/sampling.html. There are different methods depending on…
-
SSAO got merged in #7402, but there's still a lot we can do better.
## Performance
- [ ] Faster depth->world position (see reverted code)
- [ ] Render at half resolution and use a bilateral upsample
…
JMS55 updated
1 month ago
-
@mbabadi writes:
> After a certain version of Pyro (I didn't keep track), model sampling sites without matching guide sampling sites are acceptable (no exception is thrown). I believe the current b…
-
Thanks for this project, its much faster and way easier to get working than the rnnlib versions were (and faster than the tensorflow version too).
I've got everything working nicely, but have been …
-
Let's assume that one wants to have both hammers and dampers sensors. If my understanding is correct, current firmware require wiring *all* hammers (via SCA boards) to one IPS board and *all* dampers …
-
### Your current environment
The output of `python collect_env.py`
```text
Collecting environment information...
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch…