Hugging Face's logo

Hugging Face Sheets

community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

frascuchon  new activity 1 day ago
aisheets/sheets:feature request: download as Parquet?
frascuchon  new activity 3 days ago
aisheets/sheets:Is there a way to delete columns?
Ameeeee  new activity 3 days ago
aisheets/sheets:great product .. can we drag entire row vs 1 column at a time ?
View all activity

aisheets's activity

frascuchon 
in aisheets/sheets 1 day ago

feature request: download as Parquet?

❤️ ➕ 1
2
#1 opened 4 days ago by
julien-c
frascuchon 
in aisheets/sheets 3 days ago

Is there a way to delete columns?

➕ 1
1
#5 opened 3 days ago by
ParulPandey
Ameeeee 
in aisheets/sheets 3 days ago

great product .. can we drag entire row vs 1 column at a time ?

➕ ❤️ 2
1
#4 opened 4 days ago by
pulkitmehtawork
frascuchon 
posted an update 4 days ago
view post
Post
1162
Unlock the full potential of your datasets with SHEETS! It's incredibly easy to extend existing datasets and unlock new insights.

Leverage open-source models to translate, summarize, classify, and more - all directly within your existing columns.

Ready to give it a try? Explore the possibilities here: aisheets/sheets
  • 2 replies
·
dvilasuero 
in aisheets/sheets 4 days ago

feature request: download as Parquet?

➕ ❤️ 1
2
#1 opened 4 days ago by
julien-c

Direct way to upload dataset to Hub?

2
#2 opened 4 days ago by
julien-c
Ameeeee 
posted an update 4 days ago
view post
Post
1591
With Sheets, try a new way to create structured content with the help of AI!

No installs. No login. Just open a link and 🤩

This app lets you create a dataset by importing a file or starting from a prompt.

What’s different about SHEETS?
🔎 Web search integration to ground answers in real-world data
📚 In-context learning from validated sources
🔗 Transparent sourcing — every result is linked
🧩 Runs on multiple open-source models

Fight hallucinations and start creating content you can rely on.
dvilasuero 
posted an update 4 days ago
view post
Post
2319
Super excited to launch Hugging Face Sheets: Spreadsheets meet AI and unstructured data.

A few months ago, we started imagining new ways to build and transform datasets with the latest open-source models.

Today, I'm thrilled to introduce our first step in this direction.


In a nutshell:

📁 Effortlessly run prompts and models over your data.
🌐 Agentic search for accuracy and real-time information.
🖼️ Familiar, minimalistic interface for interacting with data.
🎯 Human feedback 2.0: Your input directly improves generated data.
💯 Access hundreds of open models and leading inference providers.

Go to this space to try it out!

aisheets/sheets

Leave your questions below, we're just getting started!
  • 1 reply
·
dvilasuero 
updated 2 Spaces 4 days ago
dvilasuero 
published a Space 4 days ago
frascuchon 
posted an update 12 days ago
view post
Post
2963
Hey! I built RAG MCP Server Space, a simple Gradio MCP server for RAG systems that allows you to search relevant results without passing huge contexts to your LLM.

You can use this space to integrate with your agents and improve the efficiency of your search results. Feel free to try it out and let me know if you have any feedback or questions!

frascuchon/rag-mcp-server

Thanks for checking it out!
frascuchon 
updated a Space 18 days ago
lvwerra 
authored a paper 2 months ago
lvwerra 
authored a paper 4 months ago
lvwerra 
authored a paper 5 months ago
dvilasuero 
authored a paper 6 months ago
dvilasuero 
posted an update 6 months ago
view post
Post
2763
🌐 Announcing Global-MMLU: an improved MMLU Open dataset with evaluation coverage across 42 languages, built with Argilla and the Hugging Face community.

Global-MMLU is the result of months of work with the goal of advancing Multilingual LLM evaluation. It's been an amazing open science effort with collaborators from Cohere For AI, Mila - Quebec Artificial Intelligence Institute, EPFL, Massachusetts Institute of Technology, AI Singapore, National University of Singapore, KAIST, Instituto Superior Técnico, Carnegie Mellon University, CONICET, and University of Buenos Aires.

🏷️ +200 contributors used Argilla MMLU questions where regional, dialect, or cultural knowledge was required to answer correctly. 85% of the questions required Western-centric knowledge!

Thanks to this annotation process, the open dataset contains two subsets:

1. 🗽 Culturally Agnostic: no specific regional, cultural knowledge is required.
2. ⚖️ Culturally Sensitive: requires dialect, cultural knowledge or geographic knowledge to answer correctly.

Moreover, we provide high quality translations of 25 out of 42 languages, thanks again to the community and professional annotators leveraging Argilla on the Hub.

I hope this will ensure a better understanding of the limitations and challenges for making open AI useful for many languages.

Dataset: https://huggingface.co/datasets/CohereForAI/Global-MMLU
frascuchon 
posted an update 7 months ago
view post
Post
559
🚀 Argilla v2.5.0 is out! 🎉
We’re excited to announce the latest version of Argilla, packed with features to make your data annotation workflows more powerful and seamless. Here’s what’s new:

✨ 1. Argilla Webhooks
With Argilla webhooks, you can:
* Trigger custom workflows
* Seamlessly integrate with external tools
* Build custom event-driven pipelines

🐍 2. Support for Python 3.13 and Pydantic v2
Argilla v2.5.0 now runs on:
* Python 3.13 for enhanced compatibility and speed
* Pydantic v2 for improved performance and type validation

🎨 3. Redesigned Home Page
Argilla's home page has been redesigned to provide a better user experience, showing a new
dataset card view, which provides a better overview of the datasets and annotation progress.

📖 Read the full release notes 👉 https://github.com/argilla-io/argilla/releases/tag/v2.5.0)
⬇️ Update now 👉 https://pypi.org/project/argilla)
or use the live demo 👉 argilla/argilla-template-space
dvilasuero 
posted an update 7 months ago