320 130 819

Maxime Labonne PRO

mlabonne

https://mlabonne.github.io/blog

AI & ML interests

Post-training, model editing, quantization

Recent Activity

updated a dataset about 8 hours ago

mlabonne/orca-agentinstruct-1M-v1-cleaned

updated a dataset 1 day ago

mlabonne/WildGPT-4-HF

published a dataset 1 day ago

mlabonne/WildGPT-4-HF

View all activity

Articles

Organizations

mlabonne's activity

updated a dataset about 8 hours ago

mlabonne/orca-agentinstruct-1M-v1-cleaned

Viewer • Updated about 8 hours ago • 1.05M • 243 • 54

updated a dataset 1 day ago

mlabonne/WildGPT-4-HF

Viewer • Updated 1 day ago • 66.3k • 4 • 1

published 2 datasets 1 day ago

mlabonne/WildGPT-4-HF

Viewer • Updated 1 day ago • 66.3k • 4 • 1

mlabonne/EightAya

Viewer • Updated 1 day ago • 22.2k • 4 • 1

updated a dataset 1 day ago

mlabonne/EightAya

Viewer • Updated 1 day ago • 22.2k • 4 • 1

replied to m-ric's post 1 day ago

hahaha

reacted to m-ric's post with ❤️🔥👀 1 day ago

Post

1232

Today we make the biggest release in smolagents so far: 𝘄𝗲 𝗲𝗻𝗮𝗯𝗹𝗲 𝘃𝗶𝘀𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀, 𝘄𝗵𝗶𝗰𝗵 𝗮𝗹𝗹𝗼𝘄𝘀 𝘁𝗼 𝗯𝘂𝗶𝗹𝗱 𝗽𝗼𝘄𝗲𝗿𝗳𝘂𝗹 𝘄𝗲𝗯 𝗯𝗿𝗼𝘄𝘀𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁𝘀! 🥳

Our agents can now casually open up a web browser, and navigate on it by scrolling, clicking elements on the webpage, going back, just like a user would.

The demo below shows Claude-3.5-Sonnet browsing GitHub for task: "Find how many commits the author of the current top trending repo did over last year."
Hi @mlabonne !

Go try it out, it's the most cracked agentic stuff I've seen in a while 🤯 (well, along with OpenAI's Operator who beat us by one day)

For more detail, read our announcement blog 👉 https://huggingface.co/blog/smolagents-can-see
The code for the web browser example is here 👉 https://github.com/huggingface/smolagents/blob/main/examples/vlm_web_browser.py