Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ tags:
|
|
| 10 |
pipeline_tag: visual-question-answering
|
| 11 |
---
|
| 12 |
# VL-Reasoner-7B
|
|
|
|
|
|
|
| 13 |
**VL-Reasoner-7B** achieves superior results on various multimodal reasoning benchmarks.
|
| 14 |
|
| 15 |
It is trained using the **GRPO-SSR** techniques, serving as the foundation for [**VL-Rethinker**](https://huggingface.co/TIGER-Lab/VL-Rethinker-7B/).
|
|
@@ -20,7 +22,7 @@ For details of training and evaluation, please see our [code repo](https://githu
|
|
| 20 |
|
| 21 |
Explore further via the following links:
|
| 22 |
|
| 23 |
-
| [**🚀Project Page**](https://tiger-ai-lab.github.io/VL-Rethinker/) | [**📖Paper**](https://arxiv.org/abs/2504.08837) | [**🔗Github**](https://github.com/TIGER-AI-Lab/VL-Rethinker/) | [**🤗Data**
|
| 24 |
|
| 25 |
## Citation
|
| 26 |
|
|
|
|
| 10 |
pipeline_tag: visual-question-answering
|
| 11 |
---
|
| 12 |
# VL-Reasoner-7B
|
| 13 |
+
**🚀 News:** <u>We release our meticulously curated collection of RL training queries for multimodal reasoning: [ViRL39K](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).</u>
|
| 14 |
+
|
| 15 |
**VL-Reasoner-7B** achieves superior results on various multimodal reasoning benchmarks.
|
| 16 |
|
| 17 |
It is trained using the **GRPO-SSR** techniques, serving as the foundation for [**VL-Rethinker**](https://huggingface.co/TIGER-Lab/VL-Rethinker-7B/).
|
|
|
|
| 22 |
|
| 23 |
Explore further via the following links:
|
| 24 |
|
| 25 |
+
| [**🚀Project Page**](https://tiger-ai-lab.github.io/VL-Rethinker/) | [**📖Paper**](https://arxiv.org/abs/2504.08837) | [**🔗Github**](https://github.com/TIGER-AI-Lab/VL-Rethinker/) | [**🤗Data**](https://huggingface.co/datasets/TIGER-Lab/ViRL39K) |
|
| 26 |
|
| 27 |
## Citation
|
| 28 |
|