graph-based-captions/GBC10M download history
graph-based-captions/GBC10M is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,054 times (176 in the last 7 days), and 12,504 times in total. It ranks #18,593 among datasets by monthly downloads.
Graph-based captioning (GBC) is a new image annotation paradigm that combines the strengths of long captions, region captions, and scene graphs GBC interconnects region captions to create a unified description akin to a long caption, while also providing structural information similar
Models trained on GBC10M
13 models list it as training data.
- KBlueLeaf/TIPO-500M-ft 55.9K downloads in 30 days
- KBlueLeaf/TIPO-500M 28.2K downloads in 30 days
- KBlueLeaf/TIPO-200M-ft2 8.1K downloads in 30 days
- KBlueLeaf/TIPO-100M 3.1K downloads in 30 days
- KBlueLeaf/TIPO-200M-ft 1.6K downloads in 30 days
- QuantFactory/TIPO-200M-ft-GGUF 1.2K downloads in 30 days
- KBlueLeaf/TIPO-200M 852 downloads in 30 days
- mradermacher/TIPO-500M-ft-i1-GGUF 845 downloads in 30 days
- QuantFactory/TIPO-500M-GGUF 820 downloads in 30 days
- QuantFactory/TITPOP-200M-dev-GGUF 307 downloads in 30 days
- mradermacher/TIPO-500M-ft-GGUF 206 downloads in 30 days
- graph-based-captions/GBC10M-PromptGen-200M 35 downloads in 30 days
Open graph-based-captions/GBC10M on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.