PAPOGalaxy/PAPO_ViRL39K_train download history
PAPOGalaxy/PAPO_ViRL39K_train is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 706 times (164 in the last 7 days), and 16,258 times in total. It ranks #25,191 among datasets by monthly downloads.
This is the official release of the training data for paper PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning. Hugging Face Paper: https://huggingface.co/papers/2507.06448 Project page: https://mikewangwzhl.github.io/PAPO/ This dataset is the train split of the training dataset fo
Models trained on PAPO_ViRL39K_train
13 models list it as training data.
- mradermacher/VGPO-RL-7B-i1-GGUF 973 downloads in 30 days
- mradermacher/NAS-PO-GRPO-Qwen3-VL-8B-GGUF 653 downloads in 30 days
- mradermacher/VGPO-RL-32B-i1-GGUF 522 downloads in 30 days
- mradermacher/VGPO-RL-7B-GGUF 205 downloads in 30 days
- mradermacher/VGPO-RL-32B-GGUF 162 downloads in 30 days
- MuMing0102/VGPO-RL-7B 27 downloads in 30 days
- ANke121/NAS-PO-GRPO-Qwen3-VL-8B 20 downloads in 30 days
- ANke121/NAS-PO-DAPO-Qwen3-VL-8B 14 downloads in 30 days
- MuMing0102/VGPO-RL-32B 14 downloads in 30 days
- ANke121/NAS-PO-GSPO-Qwen3-VL-8B 13 downloads in 30 days
- ANke121/NAS-PO-GSPO-Qwen3-VL-32B 5 downloads in 30 days
- ANke121/NAS-PO-DAPO-Qwen3-VL-32B 5 downloads in 30 days