chamber111/VPPO_ViRL39K_train download history
chamber111/VPPO_ViRL39K_train is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 218 times (62 in the last 7 days), and 9,824 times in total. It ranks #63,032 among datasets by monthly downloads.
Dataset Card for VPPO_ViRL39K_train Dataset Details Dataset Description This dataset is the official training split used to fine-tune the VPPO-7B and VPPO-32B models presented in our paper, "Spotlight on Token Perception for Multimodal Reinforcement Learning". This i
Models trained on VPPO_ViRL39K_train
8 models list it as training data.
- mradermacher/VPPO-7B-i1-GGUF 983 downloads in 30 days
- mradermacher/VPPO-32B-i1-GGUF 946 downloads in 30 days
- mradermacher/VPPO-32B-GGUF 542 downloads in 30 days
- mradermacher/VPPO-7B-GGUF 512 downloads in 30 days
- mradermacher/VPPO-8B-GGUF 345 downloads in 30 days
- chamber111/VPPO-8B 70 downloads in 30 days
- chamber111/VPPO-7B 29 downloads in 30 days
- chamber111/VPPO-32B 20 downloads in 30 days
Open chamber111/VPPO_ViRL39K_train on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.