BigScience Data

non-profit

https://bigscience.huggingface.co

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Zaid authored a paper 1 day ago

Masader: Metadata Sourcing for Arabic Text and Speech Data Resources

Zaid authored a paper 1 day ago

Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic

Zaid authored a paper 1 day ago

Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training

View all activity

bigscience-data's activity

albertvillanova

posted an update 1 day ago

Post

184

New in smolagents v1.17.0:
- Structured generation in CodeAgent 🧱
- Streamable HTTP MCP support 🌐
- Agent.run() returns rich RunResult 📦

Smarter agents, smoother workflows.
Try it now: https://github.com/huggingface/smolagents/releases/tag/v1.17.0

Zaid

authored 5 papers 1 day ago

Masader: Metadata Sourcing for Arabic Text and Speech Data Resources

Paper • 2110.06744 • Published Oct 13, 2021

Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic

Paper • 2412.04277 • Published Dec 5, 2024

Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training

Paper • 2410.20796 • Published Oct 28, 2024

Ashaar: Automatic Analysis and Generation of Arabic Poetry Using Deep Learning Approaches

Paper • 2307.06218 • Published Jul 12, 2023

MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs

Paper • 2505.19800 • Published 2 days ago • 1

mariagrandury

authored 2 papers 3 days ago

Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation

Paper • 2504.07072 • Published Apr 9 • 9

It's the same but not the same: Do LLMs distinguish Spanish varieties?

Paper • 2504.20049 • Published Apr 8

crystina-z

authored a paper 3 days ago

Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval

Paper • 2505.16967 • Published 6 days ago • 22

loubnabnl

posted an update 12 days ago

Post

2528

SmolVLM is now available on PocketPal — you can run it offline on your smartphone to interpret the world around you. 🌍📱

And check out this real-time camera demo by @ngxson , powered by llama.cpp:
https://github.com/ngxson/smolvlm-realtime-webcam
https://x.com/pocketpal_ai

3 replies

albertvillanova

posted an update 13 days ago

Post

2347

New in smolagents v1.16.0:
🔍 Bing support in WebSearchTool
🐍 Custom functions & executor_kwargs in LocalPythonExecutor
🔧 Streaming GradioUI fixes
🌐 Local web agents via api_base & api_key
📚 Better docs

👉 https://github.com/huggingface/smolagents/releases/tag/v1.16.0

Muennighoff

authored a paper 19 days ago

Crosslingual Reasoning through Test-Time Scaling

Paper • 2505.05408 • Published 20 days ago • 8

giadap

posted an update 21 days ago

Post

4187

Ever notice how some AI assistants feel like tools while others feel like companions? Turns out, it's not always about fancy tech upgrades, because sometimes it's just clever design.

Our latest blog post at Hugging Face dives into how minimal design choices can completely transform how users experience AI. We've seen our community turn the same base models into everything from swimming coaches to interview prep specialists with surprisingly small tweaks.

The most fascinating part? When we tested identical models with different "personalities" in our Inference Playground, the results were mind-blowing.

Want to experiment yourself? Our Inference Playground lets anyone (yes, even non-coders!) test these differences in real-time. You can:

- Compare multiple models side-by-side
- Customize system prompts
- Adjust parameters like temperature
- Test multi-turn conversations

It's fascinating how a few lines of instruction text can transform the same AI from strictly professional to seemingly caring and personal, without changing a single line of code in the model itself.

Read more here: https://huggingface.co/blog/giadap/ai-personas

Muennighoff

authored a paper 28 days ago

ReasonIR: Training Retrievers for Reasoning Tasks

Paper • 2504.20595 • Published 29 days ago • 54

Pclanglais

authored a paper 29 days ago

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

Paper • 2504.18225 • Published Apr 25 • 12

meg

posted an update about 1 month ago

Post

2518

New launch: See the energy use of chatbot conversations, in real time. =)
jdelavande/chat-ui-energy
Great work from @JulienDelavande !

mpatwary

authored a paper about 1 month ago

NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning

Paper • 2504.13941 • Published Apr 15 • 10

albertvillanova

posted an update about 1 month ago

Post

2704

smolagents v1.14.0 is out! 🚀
🔌 MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
🪨 Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. 💼

Full release 👉 https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI

giadap

posted an update about 1 month ago

Post

1667

🤗 Just published: "Consent by Design" - exploring how we're building better consent mechanisms across the HF ecosystem!

Our research shows open AI development enables:
- Community-driven ethical standards
- Transparent accountability
- Context-specific implementations
- Privacy as core infrastructure

Check out our Space Privacy Analyzer tool that automatically generates privacy summaries of applications!

Effective consent isn't about perfect policies; it's about architectures that empower users while enabling innovation. 🚀

Read more: https://huggingface.co/blog/giadap/consent-by-design

3 replies

yjernite

posted an update about 1 month ago

Post

3291

Today in Privacy & AI Tooling - introducing a nifty new tool to examine where data goes in open-source apps on 🤗

HF Spaces have tons (100Ks!) of cool demos leveraging or examining AI systems - and because most of them are OSS we can see exactly how they handle user data 📚🔍

That requires actually reading the code though, which isn't always easy or quick! Good news: code LMs have gotten pretty good at automatic review, so we can offload some of the work - here I'm using Qwen/Qwen2.5-Coder-32B-Instruct to generate reports and it works pretty OK 🙌

The app works in three stages:
1. Download all code files
2. Use the Code LM to generate a detailed report pointing to code where data is transferred/(AI-)processed (screen 1)
3. Summarize the app's main functionality and data journeys (screen 2)
4. Build a Privacy TLDR with those inputs

It comes with a bunch of pre-reviewed apps/Spaces, great to see how many process data locally or through (private) HF endpoints 🤗

Note that this is a POC, lots of exciting work to do to make it more robust, so:
- try it: yjernite/space-privacy
- reach out to collab: yjernite/space-privacy

AI & ML interests

Recent Activity

Team members 72

bigscience-data's activity