Jupyter Agent

jupyter-agent's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

freddyaboulton 

posted an update 5 days ago

view post

Post

1141

Gradio 6.0 is launching this year!

We're revamping the core to give you performance improvements and unprecedented customization. Build better, faster.

Check out the GitHub milestone to learn what's planned under the hood!

https://github.com/gradio-app/gradio/issues?q=is:issue%20state:open%20milestone:%22Gradio%206%22

See translation

• 

🔥

4

4

🤗

2

2

👍

1

1

+

Reply

hannayukhymenko 

updated a dataset 12 days ago

jupyter-agent/jupyter-agent-dataset

Viewer • Updated 12 days ago • 95.8k • 5.78k • 141

hannayukhymenko 

updated a collection 12 days ago

Jupyter Agent

Collection

Blog: https://huggingface.co/blog/jupyter-agent-2 • 4 items • Updated 10 days ago • 1

hannayukhymenko 

updated 2 models 12 days ago

jupyter-agent/jupyter-agent-qwen3-4b-thinking

Text Generation • 4B • Updated 12 days ago • 283 • 5

jupyter-agent/jupyter-agent-qwen3-4b-instruct

Text Generation • 4B • Updated 12 days ago • 264 • 5

baptistecolle 

published 2 models 12 days ago

jupyter-agent/jupyter-agent-qwen3-4b-thinking

Text Generation • 4B • Updated 12 days ago • 283 • 5

jupyter-agent/jupyter-agent-qwen3-4b-instruct

Text Generation • 4B • Updated 12 days ago • 264 • 5

baptistecolle 

updated 2 models 13 days ago

jupyter-agent/jupyter-agent-qwen3-4b-instruct

Text Generation • 4B • Updated 12 days ago • 264 • 5

jupyter-agent/jupyter-agent-qwen3-4b-thinking

Text Generation • 4B • Updated 12 days ago • 283 • 5

hannayukhymenko 

in jupyter-agent/jupyter-agent-dataset 17 days ago

[bot] Conversion to Parquet

#2 opened 18 days ago by

parquet-converter

hannayukhymenko 

posted an update 20 days ago

view post

Post

2655

Releasing the Jupyter Agent Dataset! 🚀

Built from 7 TB of real Kaggle datasets + 20k notebooks, creating real code exec traces using Qwen3-Coder and E2B.
Training on this data dramatically improves the ability to execute code and analyze data.

We ( @baptistecolle @hannayukhymenko @lvwerra ) have created a novel synthetic data generation pipeline with efficient scaffolding, which gives a big performance boost after training your coding agent🔥With the help of real Kaggle notebooks and datasets we generate synthetic notebooks which aim to analyze datasets and answer factual questions about them more efficiently. We simulate a real code execution environment by prompting LLMs or with the help of E2B sandboxes. We have built a dataset of 50k+ high-quality LLM-generated notebooks which can help your agent become better at performing data analysis and question answering.

Link: https://huggingface.co/datasets/data-agents/jupyter-agent-dataset

See translation

• 

• 
• 
• 3 replies

·

👍

6

6

🚀

1

1

+

Reply

eggie5 

authored a paper about 1 month ago

DABstep: Data Agent Benchmark for Multi-step Reasoning

Paper • 2506.23719 • Published Jun 30

thomwolf 

authored a paper 3 months ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published Jun 26 • 71

lvwerra 

authored a paper 3 months ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published Jun 26 • 71

freddyaboulton 

posted an update 3 months ago

view post

Post

3902

The new multimodalart/self-forcing model and demo are truly impressive!

See translation

🔥

4

4

+

Reply

freddyaboulton 

posted an update 3 months ago

view post

Post

614

Time is running out! ⏰

Less than 24 hours to participate in the MCP Hackathon and win thousands of dollars in prizes! Don't miss this opportunity to showcase your skills.

Visit Agents-MCP-Hackathon/AI-Marketing-Content-Creator to register!

See translation

• 

🤗

1

1

+

Reply

freddyaboulton 

posted an update 3 months ago

view post

Post

451

🚨 NotebookLM Dethroned?! 🚨

Meet Fluxions vui: The new open-source dialogue generation model.
🤯 100M Params, 40k hours audio!
🎙️ Multi-speaker audio
😂 Non-speech sounds (like [laughs]!)
📜 MIT License

Is this the future of content creation? Watch the video and decide for yourself!

https://huggingface.co/spaces/fluxions/vui-spacehttps://huggingface.co/fluxions/vui

See translation

• 
• 1 reply

·

👍

1

1

+

Reply