Loading video...
Video Failed to Load
We're launching Computer Use in smolagents! 🥳 -> As vision models become more capable, they become able to power complex agentic workflows. Especially Qwen-VL models, that support built-in grounding, i.e. ability to locate any element in an image by its coordinates, thus to click any item on a screenshot.... show more
43,850 views • 1 year ago •via X (Twitter)
11 Comments

m_ric1 year ago
Try the demo here 👉

MightyBot1 year ago
🧠 Unified Search. Smarter Meetings. Effortless CRM. MightyBot is your AI agent platform for seamless workflows—record meetings, automate CRM updates, and find answers across apps in seconds. 🌟 Focus on what matters. We'll handle the grind.

Dhruv Diddi1 year ago
@Thom_Wolf Multimodal models are going to pick up real fast ⚡️

Oli1 year ago
i think ui tars 1.5 7b would work better here its much better at this

Piyush1 year ago
Awesome! Gonna try this out! 😁

ぽいロード@音技術者1 year ago
Hey Computer use AI ,please use 3d modeling soft and create this

Van Tuan Bui1 year ago
Congrats on the launch! 🎉

Sam Woods1 year ago
Smolagents with computer use powered by vision models like Qwen-VL sounds really powerful

蕭夫SioFU1 year ago
@huggingface cool

Trelis Research1 year ago
nice, what vlms did you test out that work best?

gladosb51 year ago
hmmmmmm


