Add project page to model card
Browse filesThis PR adds a project page URL to the model card.
README.md
CHANGED
|
@@ -25,7 +25,6 @@ tags:
|
|
| 25 |
|
| 26 |
The V-Triune system enables VLMs to be jointly optimized on diverse multimodal tasks within a single, cohesive training pipeline. Orsta-7B has been specifically trained using V-Triune on a carefully curated set of eight challenging visual tasks, fostering robust generalization and enhanced capabilities.
|
| 27 |
|
| 28 |
-
|
| 29 |
## Training with V-Triune
|
| 30 |
|
| 31 |
Orsta-32B-0326's advanced abilities stem from its training with the V-Triune system. Key aspects of its training include:
|
|
@@ -71,4 +70,7 @@ If you use Orsta-32B-0326 or the V-Triune system in your research, please cite o
|
|
| 71 |
journal={arXiv preprint arXiv:2505.18129},
|
| 72 |
year={2025}
|
| 73 |
}
|
| 74 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
The V-Triune system enables VLMs to be jointly optimized on diverse multimodal tasks within a single, cohesive training pipeline. Orsta-7B has been specifically trained using V-Triune on a carefully curated set of eight challenging visual tasks, fostering robust generalization and enhanced capabilities.
|
| 27 |
|
|
|
|
| 28 |
## Training with V-Triune
|
| 29 |
|
| 30 |
Orsta-32B-0326's advanced abilities stem from its training with the V-Triune system. Key aspects of its training include:
|
|
|
|
| 70 |
journal={arXiv preprint arXiv:2505.18129},
|
| 71 |
year={2025}
|
| 72 |
}
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
## Project Page
|
| 76 |
+
https://github.com/MiniMax-AI/One-RL-to-See-Them-All.
|