ScreenVLM

Description

ScreenVLM is an open-weight text-generation model published by docling-project on the Hugging Face Hub. It has 1,069 downloads. Runs with transformers.

Categories

• Productivity
• Design

Tags

• idefics3
• image-text-to-text
• text-generation
• screen-parsing
• ui-understanding
• object-detection
• grounding
• web

Capabilities

• Text generation
• Conversational
• Library: transformers