search

OpenAdaptAI / OpenAdapt

AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models
https://www.OpenAdapt.AI
MIT License
850 stars 109 forks source link

Implement Set-of-Mark (SOM) with ollama #547

Open abrichr opened 9 months ago

abrichr commented 9 months ago

Feature request

Set-of-Mark: https://github.com/OpenAdaptAI/OpenAdapt/issues/519

ollama: https://github.com/OpenAdaptAI/OpenAdapt/issues/546

Motivation

Open + offline state-of-the-art visual understanding

abrichr commented 8 months ago

Related:

https://github.com/IDEA-Research/Grounded-Segment-Anything https://github.com/SkalskiP/SoM https://github.com/CASIA-IVA-Lab/FastSAM