Add pipeline tag and improve metadata
Browse filesHi! I'm Niels from the Hugging Face community team.
I noticed this model card is missing some metadata. I've added `pipeline_tag: image-feature-extraction` to the YAML section to make the model more discoverable for users interested in visual tokenization and feature extraction.
I've also ensured the paper, code, and project links are correctly formatted and easy to find.
README.md
CHANGED
|
@@ -1,11 +1,13 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- model_hub_mixin
|
| 4 |
- pytorch_model_hub_mixin
|
| 5 |
-
license: apache-2.0
|
| 6 |
---
|
|
|
|
| 7 |
# Communication-Inspired Tokenization for Structured Image Representations
|
| 8 |
-
|
| 9 |
<p align="left">
|
| 10 |
<a href="https://araachie.github.io">Aram Davtyan</a> •
|
| 11 |
<a href="https://www.cvg.unibe.ch/people/sahin">Yusuf Sahin</a> •
|
|
@@ -16,21 +18,23 @@ license: apache-2.0
|
|
| 16 |
<a href="https://www.cvg.unibe.ch/people/favaro">Paolo Favaro</a>
|
| 17 |
</p>
|
| 18 |
|
| 19 |
-
Official pre-trained models for the paper: https://
|
| 20 |
|
| 21 |
-
Project
|
| 22 |
|
| 23 |
## Installation
|
| 24 |
|
| 25 |
-
Follow the instructions at https://github.com/Araachie/comit
|
| 26 |
|
| 27 |
## Usage
|
| 28 |
|
| 29 |
Example usage, downloading `COMiT-B` from the Hugging Face Hub:
|
| 30 |
|
| 31 |
```python
|
|
|
|
| 32 |
from comit import COMiT
|
| 33 |
|
|
|
|
| 34 |
model = COMiT.from_pretrained('cvg-unibe/comit-b')
|
| 35 |
model.eval().to(device)
|
| 36 |
```
|
|
@@ -84,7 +88,7 @@ with torch.no_grad():
|
|
| 84 |
## Licensing
|
| 85 |
|
| 86 |
Unless otherwise noted, the model weights are licensed under Apache license 2.0.
|
| 87 |
-
For the code licensing, see https://github.com/Araachie/comit?tab=readme-ov-file#licensing
|
| 88 |
|
| 89 |
## Citation
|
| 90 |
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: image-feature-extraction
|
| 4 |
tags:
|
| 5 |
- model_hub_mixin
|
| 6 |
- pytorch_model_hub_mixin
|
|
|
|
| 7 |
---
|
| 8 |
+
|
| 9 |
# Communication-Inspired Tokenization for Structured Image Representations
|
| 10 |
+
|
| 11 |
<p align="left">
|
| 12 |
<a href="https://araachie.github.io">Aram Davtyan</a> •
|
| 13 |
<a href="https://www.cvg.unibe.ch/people/sahin">Yusuf Sahin</a> •
|
|
|
|
| 18 |
<a href="https://www.cvg.unibe.ch/people/favaro">Paolo Favaro</a>
|
| 19 |
</p>
|
| 20 |
|
| 21 |
+
Official pre-trained models for the paper: [Communication-Inspired Tokenization for Structured Image Representations](https://huggingface.co/papers/2602.20731).
|
| 22 |
|
| 23 |
+
[Project Website](https://araachie.github.io/comit/) | [GitHub Repository](https://github.com/Araachie/comit)
|
| 24 |
|
| 25 |
## Installation
|
| 26 |
|
| 27 |
+
Follow the instructions at [https://github.com/Araachie/comit](https://github.com/Araachie/comit)
|
| 28 |
|
| 29 |
## Usage
|
| 30 |
|
| 31 |
Example usage, downloading `COMiT-B` from the Hugging Face Hub:
|
| 32 |
|
| 33 |
```python
|
| 34 |
+
import torch
|
| 35 |
from comit import COMiT
|
| 36 |
|
| 37 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 38 |
model = COMiT.from_pretrained('cvg-unibe/comit-b')
|
| 39 |
model.eval().to(device)
|
| 40 |
```
|
|
|
|
| 88 |
## Licensing
|
| 89 |
|
| 90 |
Unless otherwise noted, the model weights are licensed under Apache license 2.0.
|
| 91 |
+
For the code licensing, see [https://github.com/Araachie/comit?tab=readme-ov-file#licensing](https://github.com/Araachie/comit?tab=readme-ov-file#licensing)
|
| 92 |
|
| 93 |
## Citation
|
| 94 |
|