-
### Bug description
I'm running an LSTM-based model training on Kaggle. I use Pytorch Lightning and wandb logger for that.
That's my model's class:
```
class Model(pl.LightningModule):
…
-
### Describe the bug
I am using the training script documented here https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md to train a LORA on my dataset.
here is th…
-
### Motivation
I propose to add `input_embeds` as an optional input to the generation params.
# Why is this important
Nowadays there are a lot of Vision Language Models (VLMs) and they all h…
-
Once a job has been dropped from the queue, it would be great if AiiDA would query the scheduler for the job status rather than assuming that the job completed correctly (e.g. to detect whether the wa…
-
## Description
When using pallets that can make calls to other pallets, having a mechanism to filter out these calls would be very helpful.
## Motivation
It may be necessary to filter out unwanted …
-
Please improve the fine-tuning script!
After I solved this problem:
```
Traceback (most recent call last):
File "E:\OmniGen\train.py", line 371, in
main(args)
File "E:\OmniGen\train.py"…
-
When I replaced the model in the tutorial with my own other model, this error occurred：
This is my code：
student_model = STU_IAT().cuda()
#student_model = STU_IAT()
if config.pretrain_dir is not N…
-
## Issue description
I am based on the POMO code [POMO](https://github.com/yd-kwon/POMO) to change it to a single machine multi-GPU graphics card running mode
Let me explain the specific code lo…
-
## Feature Request
### Describe your feature request-related problem
We try to add scatter for a table with nine indexes, which makes PD CPU increase to 2000%.
Because it will add n+1 scatter…
-
### What happened?
Scheduler throughput and Performance has regressed in 1.31 when compared to 1.30
### What did you expect to happen?
Scheduler throughput and Performance should at least sta…