Ricky06662/VisionReasoner_multi_object_1k_840 download history

Ricky06662/VisionReasoner_multi_object_1k_840 is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 67 times (24 in the last 7 days), and 2,771 times in total. It ranks #151,092 among datasets by monthly downloads.

This dataset is used in VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning. Github repository: https://github.com/dvlab-research/VisionReasoner

Open Ricky06662/VisionReasoner_multi_object_1k_840 on Hugging Face