-
### Discussion
Firstly, Wish you have a nice day on Chinese New Year.
I am currently catching up with your progress in integrating Qwen1.5 to this project. Since the Qwen1.5 shares a similar struc…
-
The datasets provided in the original GATO paper are varied and numerous. We need a preliminary analysis of what data is availability, what data has equivalents, and what data is not clearly source ab…
-
### Question
I noticed during the fine-tuning phase that in the OCR_VQA dataset, there are many GIF files, but they have all been changed to JPG in the JSON. Can these files be directly modified by c…
-
In order to make comparing different image recognition methods easier, it would help if the tables and charts included the augmentations used by the papers. Image recogntion can be made easier by augm…
-
### Describe the bug
Hi. I have the following app in huggingface: [link](https://huggingface.co/spaces/nlphuji/whoops_explorer).
It's a 25 rows * 4 columns of images. I have 500 images, but when …
-
微博内容精选
-
In the Prism Launcher flatpak, it seems like ffmpeg doesn't support format `rawvideo`:
```
[april@tadaima ~]$ flatpak run --command="ffmpeg" org.prismlauncher.PrismLauncher -formats
[...]
File f…
-
Hi, thanks for sharing this awesome work.
As I was trying your system more and more, a few questions popped up in my mind:
1. In my experience, I am seeing instances where the LLM starts generat…
-
The various challenges involved in making sense of an image found on social media is summarized by this image
![Screenshot 2023-12-04 at 15-13-05 Tech Interventions against Online Harms](https://gith…
-
Hi,
Could you please release the trained model weight for VQA?
Currently, the links for VQA in the pre-trained models section are the JSON file instead of the ckpt file for the model weight.
Than…