-
```python
```
### Ensure we are using caudate to its full potential
```python
from lightning.pytorch.callbacks import DeviceStatsMonitor
trainer = Trainer(callbacks=[DeviceStatsMonitor()])
…
-
I'm working on a use case where I need to execute database operations synchronously using Npgsql. However, I'm encountering a bottleneck:
1. When using synchronous execution, the application appear…
-
Didn't find the code for DDIM inversion, but DDIM sampling directly from noise, why is that?
@torch.no_grad()
def __call__(
self,
prompt: Union[str, List[str]],
mot…
-
### System Info
docker image: ```huggingface/transformers-pytorch-deepspeed-latest-gpu:latest```
- `transformers` version: 4.36.0.dev0
- Platform: Linux-6.2.0-37-generic-x86_64-with-glibc2.29
- Py…
-
I'm using the EntropyBottleneck module in a factorized prior network. While training, the aux_loss and bpp_loss are decreasing but when I use the trained network to compress and save the compressed im…
-
Hello, authors! Although quecc is designed for very low token counts, I am curious whether you have tested quecc in a higher token count range (the highest in the paper is 36). When I trained with 144…
-
**Is your feature request related to a problem? Please describe.**
The current AnimateDiffSDXLPipeline doesn't support neither 1 controlnet nor multi controlnets.
I've been working on this task for …
-
配置文件如下：
# Copyright (c) OpenMMLab. All rights reserved.
"""Data format:
[{
"messages": [
{ "role": "system", "content": "xxx." },
{ "role": "user", "content": "xxx." },
…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
- `llamafactory` version: 0.9.1.dev0
- Platform: Linux-5.4.210-4-velinux1-amd64-x86_64-with-glibc2…
-
Hello author, I have read your paper carefully and also reproduced the code. Following the steps you responded to in the other question, I ran the code.
First, I set time_batch_size=…