1 35 58

Jian Liao

imjliao

AI & ML interests

None yet

Recent Activity

liked a model 6 days ago

THUDM/cogagent-9b-20241220

liked a Space 17 days ago

Infinigence/Megrez-3B-Omni

liked a model 20 days ago

OS-Copilot/OS-Atlas-Base-7B

View all activity

Organizations

None yet

imjliao's activity

liked a model 6 days ago

THUDM/cogagent-9b-20241220

Image-Text-to-Text • Updated 8 days ago • 799 • 34

liked a Space 17 days ago

Running

🐠

Megrez 3B Omni

Megrez-3B-Omni Chat Demo

liked a model 20 days ago

OS-Copilot/OS-Atlas-Base-7B

Image-Text-to-Text • Updated Nov 19, 2024 • 4.76k • 28

liked 2 Spaces 20 days ago

Running on Zero

189

💻

ShowUI

Running on Zero

🏆

PTA 1

Controlling Computers with Small Models

liked 2 models 20 days ago

showlab/ShowUI-2B

Updated 28 days ago • 13.5k • 212

AskUI/PTA-1

Image-Text-to-Text • Updated Nov 28, 2024 • 586 • 40

reacted to maxiw's post with 🚀 20 days ago

Post

2032

You can now try out computer use models from the hub to automate your local machine with https://github.com/askui/vision-agent. 💻

import time
from askui import VisionAgent

with VisionAgent() as agent:
    agent.tools.webbrowser.open_new("http://www.google.com")
    time.sleep(0.5)
    agent.click("search field in the center of the screen", model_name="Qwen/Qwen2-VL-7B-Instruct")
    agent.type("cats")
    agent.keyboard("enter")
    time.sleep(0.5)
    agent.click("text 'Images'", model_name="AskUI/PTA-1")
    time.sleep(0.5)
    agent.click("second cat image", model_name="OS-Copilot/OS-Atlas-Base-7B")