Add metadata
Browse filesThis PR ensures a "Use this model" button appears at the top right by adding the library name.
It also adds the pipeline tag and base model (I assume it's Qwen/Qwen2.5-VL-7B-Instruct).
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# ViGoRL: Visually Grounded Reinforcement Learning for Visual Reasoning
|
| 2 |
|
| 3 |
This model card describes the ViGoRL (**Vi**sually **G**r**o**unded **R**einforcement **L**earning) model, introduced in our paper ["Grounded Reinforcement Learning for Visual Reasoning"](https://arxiv.org/abs/2505.23678).
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
pipeline_tag: image-text-to-text
|
| 4 |
+
base_model:
|
| 5 |
+
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
# ViGoRL: Visually Grounded Reinforcement Learning for Visual Reasoning
|
| 9 |
|
| 10 |
This model card describes the ViGoRL (**Vi**sually **G**r**o**unded **R**einforcement **L**earning) model, introduced in our paper ["Grounded Reinforcement Learning for Visual Reasoning"](https://arxiv.org/abs/2505.23678).
|