Hugging Face's logo

smolagents
Team
community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

andito  authored a paper 18 days ago
FineVision: Open Data Is All You Need
thomwolf  authored a paper 25 days ago
Robot Learning: A Tutorial
lvwerra  authored a paper 26 days ago
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
View all activity

evalstate 
posted an update 1 day ago
view post
Post
1463
Hugging Face MCP Server v0.2.40
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Improved progressive disclosure and descriptions for Jobs tool.
abidlabs 
posted an update 5 days ago
view post
Post
7258
Why I think local, open-source models will eventually win.

The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.

In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.

An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.

Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
·
evalstate 
posted an update 13 days ago
view post
Post
283
Hugging Face MCP Server v0.2.35
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

$HF_TOKEN is expanded in Jobs Secrets environment variables.
andito 
authored a paper 18 days ago
evalstate 
posted an update 18 days ago
view post
Post
298
Hugging Face MCP Server v0.2.33
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Allow discovery of Product Documentation Library via the Search tool.
andito 
posted an update 19 days ago
view post
Post
1653
Finally, our new paper is out! "𝗙𝗶𝗻𝗲𝗩𝗶𝘀𝗶𝗼𝗻: 𝗢𝗽𝗲𝗻 𝗗𝗮𝘁𝗮 𝗜𝘀 𝗔𝗹𝗹 𝗬𝗼𝘂 𝗡𝗲𝗲𝗱"! 🥳
FineVision: Open Data Is All You Need (2510.17269)

If you've ever trained a VLM, you know this problem: nobody shares their data mixtures. It's a black box, making replicating SOTA work impossible.
We wanted to change that.

FineVision unifies 200 sources into 24 million samples. With 17.3 million images and 9.5 billion answer tokens, it's the largest open resource of its kind.

In the paper, we share how we built it:
🔍 finding and cleaning data at scale
🧹 removing excessive duplicates across sources
🤗 decontaminating against 66 public benchmarks

My favorite part is Figure 6 (in the video!). It's our visual diversity analysis. It shows that FineVision isn't just bigger; it's more balanced and conceptually richer than other open datasets.
NVIDIA's Eagle 2 paper highlighted just how critical this visual diversity is, and our results confirm it: models trained on FineVision consistently outperform those trained on any other open dataset on 11 benchmarks!

🎉 To celebrate the paper, I’m also releasing a concatenated and shuffled version of the full dataset! 👉HuggingFaceM4/FineVision_full_shuffled

It’s ready to stream, so you can start training your own models right away:

from datasets import load_dataset
d = load_dataset("HuggingFaceM4/FineVision_full_shuffled", split="train", streaming=True)
print(next(iter(d)))

A big shoutout to the first authors: Luis Wiedmann and Orr Zohar. They are rockstars!
merve 
posted an update 20 days ago
view post
Post
5094
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
·
thomwolf 
authored a paper 25 days ago
evalstate 
posted an update 25 days ago
view post
Post
231
Hugging Face MCP Server v0.2.31
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

- OpenAI Apps SDK Support for Gradio Content Generation spaces
lvwerra 
authored a paper 26 days ago
evalstate 
posted an update about 1 month ago
view post
Post
327
Hugging Face MCP Server v0.2.29
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

- Document Fetch tool now returns markdown direct from HF Docs rather than processed.
- Relative URLs accepted for Fetch
merve 
updated a collection about 2 months ago
abidlabs 
posted an update about 2 months ago
merve 
posted an update about 2 months ago
view post
Post
6625
large AI labs open-sourced a ton of models last week 🔥
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🤝
> IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset 💻 OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash 💭 meituan-longcat/LongCat-Flash-Thinking
  • 2 replies
·
A-Mahla 
updated a model about 2 months ago
A-Mahla 
updated a dataset about 2 months ago
A-Mahla 
published a dataset about 2 months ago