TIGER-Lab
/

VL-Rethinker-7B

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

JasperHaozhe commited on Apr 21

Commit

f720632

·

verified ·

1 Parent(s): 52ef36e

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -13,9 +13,11 @@ library_name: transformers
 # VL-Rethinker-7B
 **VL-Rethinker-7B** achieves SoTA results on various multimodal reasoning benchmarks.
-It is trained using the **GRPO-SSR and Forced Rethinking** techniques, using meticulously curated **training data**: [ViRL39K](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).
 For details of our approach and performance comparison, please see our [paper](https://github.com/TIGER-AI-Lab/VL-Rethinker/blob/main/paper.pdf).

 # VL-Rethinker-7B
+**🚀 News:** <u>We release our meticulously curated collection of RL training queries for multimodal reasoning: [ViRL39K](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).</u>
 **VL-Rethinker-7B** achieves SoTA results on various multimodal reasoning benchmarks.
+It is trained using the **GRPO-SSR and Forced Rethinking** techniques, using meticulously curated [ViRL39K](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).
 For details of our approach and performance comparison, please see our [paper](https://github.com/TIGER-AI-Lab/VL-Rethinker/blob/main/paper.pdf).