docling-project/ScreenVLM download history
docling-project/ScreenVLM is a 315M-parameter image text to text model by docling-project. In the last 30 days it was downloaded 864 times (195 in the last 7 days), and 4,965 times in total.
It ranks #40,434 on the Hub by monthly downloads and #3,759 among image text to text models.
It has 10 likes.
2 models build on ScreenVLM: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 1,119 times in the last 30 days. See the ScreenVLM galaxy.
Most downloaded derivatives
- Hansda/ScreenVLM-GGUF (quantized), 229 downloads in 30 days
- olragon/ScreenVLM-MLX-4bit (quantized), 26 downloads in 30 days
Open docling-project/ScreenVLM on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.