29 30 216

Kaizhao Liang PRO

kz919

https://kyleliang919.github.io/

AI & ML interests

Search = AGI?

Recent Activity

liked a dataset 20 days ago

allenai/c4

reacted to maxiw's post with 👍 26 days ago

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") ``` Currently these models are integrated with Gradio Spaces API. Also planning to add local inference soon! Currently supported: - https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct - https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct - https://huggingface.co/AskUI/PTA-1 - https://huggingface.co/OS-Copilot/OS-Atlas-Base-7B

liked a Space 27 days ago

dylanebert/3d-arena

View all activity

Organizations

kz919's activity

liked a dataset 20 days ago

allenai/c4

Viewer • Updated Jan 9, 2024 • 10.4B • 435k • 400

reacted to maxiw's post with 👍 26 days ago

Post

2419

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")

Currently these models are integrated with Gradio Spaces API. Also planning to add local inference soon!

Currently supported:
- Qwen/Qwen2-VL-7B-Instruct
- Qwen/Qwen2-VL-2B-Instruct
- AskUI/PTA-1
- OS-Copilot/OS-Atlas-Base-7B

3 replies

liked 2 Spaces 27 days ago

296

3D Arena

🏢

Vote on and view 3D leaderboard entries

398

Stable Virtual Camera

⚡

Generate virtual camera views from input images

upvoted an article about 1 month ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.22k

liked a dataset about 1 month ago

laion/laion400m

Viewer • Updated Jul 13, 2024 • 361M • 2.87k • 49

liked a Space about 2 months ago

1.14k

IC Light

📈

Generate relit images from your photo

liked a dataset about 2 months ago

timm/imagenet-1k-wds

Viewer • Updated Jan 7, 2024 • 80.7k • 4.81k • 20

liked a model about 2 months ago

microsoft/wham

Updated Feb 21 • 176 • 252

upvoted a paper about 2 months ago

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published Feb 11 • 48

upvoted a paper 2 months ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 137

liked a Space 2 months ago

915

FineWeb: decanting the web for the finest text data at scale

🍷

Generate high-quality web text data for LLM training

reacted to maxiw's post with 🤗🚀 2 months ago

Post

2419

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")