Hugging Face's logo

smolagents
Enterprise
community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

thomwolfΒ  authored a paper 18 days ago
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
lvwerraΒ  authored a paper 18 days ago
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
thomwolfΒ  authored a paper about 1 month ago
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
View all activity

merveΒ 
posted an update about 12 hours ago
view post
Post
140
past week had huuuge releases πŸ’—
here's our picks πŸ”₯ find more models, datasets, demos here merve/releases-july-11-68750452c358c98b0fa663f7

> moonshotai/Kimi-K2-Instruct is the new sota LLM with 1T total 32B active parameters 🀯

> HuggingFaceTB/SmolLM3-3B is the new best LM for it's size, offers thinking mode πŸ’­ as well as the dataset HuggingFaceTB/smoltalk2

> Alibaba-NLP/WebSailor-3B is the new agentic LLM for complex browsing

> Google DeepMind released medical vision LMs with an agentic doctor-patient app google/medgemma-release-680aade845f90bec6a3f60c4

> fal released a LoRA to improve details on face images fal/Realism-Detailer-Kontext-Dev-LoRA
albertvillanovaΒ 
posted an update 4 days ago
view post
Post
256
πŸš€ New in smolagents v1.20.0: Remote Python Execution via WebAssembly (Wasm)

We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!

πŸ”§ Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.

Why this matters:
βœ… Isolated execution = no host access
βœ… No need for Python on the user's machine
βœ… Safer evaluation of arbitrary code
βœ… Compatible with serverless / edge agent workloads
βœ… Ideal for constrained or untrusted environments

This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. πŸ’‘

πŸ’‘ We're inviting the open-source community to help evolve this executor:
β€’ Tackle more advanced Python features
β€’ Expand compatibility
β€’ Add test coverage
β€’ Shape the next-gen secure agent runtime

πŸ”— Check out the PR: https://github.com/huggingface/smolagents/pull/1261

Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.

This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together πŸ§ βš™οΈ

πŸ‘‰ https://github.com/huggingface/smolagents/releases/tag/v1.20.0

#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
merveΒ 
posted an update 6 days ago
view post
Post
2993
GitHub refuses to render notebooks for a long time now πŸ’”

so smol-vision now lives in Hugging Face model repository πŸ€— merve/smol-vision
  • 1 reply
Β·
merveΒ 
posted an update 7 days ago
view post
Post
3350
ByteDance released Tar 1.5B and 7B: image-text in image-text out models, fully open-source πŸ‘ ByteDance-Seed/tar-6864cf0d9fe59a3b91cc4260

They have an image tokenizer unified with text, and they de-tokenize using either of two models (LLM and diffusion)
The model is actually a full LLM (Qwen2), the tokenizer converts image tokens 🀯
m-ricΒ 
posted an update 7 days ago
view post
Post
2565
Diffusion LLMs are coming for autoregressive LLMs ⚑️⚑️ Inception Labs' new diffusion model demolishes all leading LLMs on generation speed, with equal quality !

Inception Labs was founded a few months ago, and they're not sleeping: after dropping a code model, they just published Mercury chat, a diffusion-based chat model that reaches 1000 tokens / second on H100, i.e. 10x more than models of equivalent performance on the same hardware!

What's the breakthrough? Well instead, of generating tokens left-to-right like the more common autoregressive LLMs, diffusion models generate their blocks of text all at once, and successive steps refine the whole text.

Diffusion models being really fast at isn't new, we have had some promising results on this by Google already back in May with Gemini Diffusion, and Mercury themselves had already published their coding model a few months ago

But being that good quality is new - and now Inception Labs just proved that their models work well in chat too, which could have been challenging given that's streaming generation is well suited to left-to-right generation.

They have a playground available at chat dot inceptionlabs dot ai, I recommend giving it a try!
  • 1 reply
Β·
merveΒ 
posted an update 7 days ago
view post
Post
3613
Huge drops in open AI past week!
Find more models, datasets, demos here merve/releases-july-4-686bcc54ed7c45c341fbf654
Some of our picks 🫑
⏯️ BAAI/MTVCraft is a new Veo3-like text-to-video model, demo is here BAAI/MTVCraft
πŸ§‘πŸ»β€πŸ’» apple/diffucoder-6868139f56672ae046fe04e8 is a new family of diffusion LLMs (7B base and instruct) for coding
πŸ—£οΈ kyutai/tts-1.6b-en_fr is a new small TTS model for English and France
πŸ‘€ aharley/alltracker is a new pixel tracking model by Stanford, demo is here aharley/alltracker
πŸ“– racineai/OGC_MEGA_MultiDomain_DocRetrieval is a new large visual document retrieval dataset
  • 1 reply
Β·
merveΒ 
posted an update 12 days ago
view post
Post
905
SOOOO MANY MODEL RELEASES 😍
Here's some picks from past week πŸ€—

> ByteDance/XVerse is a new identity preserving image generation model πŸ–ΌοΈ
> google/gemma-3n-E4B-it, any-to-text model supported by transformers πŸ€—
> nvidia/llama-nemoretriever-colembed-3b-v1 two new state-of-the-art visual document retrievers πŸ“‘
> New version of Dia TTS model is up nari-labs/Dia-1.6B-0626
> Black Forest Labs releases Kontext benchmark black-forest-labs/kontext-bench

Find more here merve/releases-june-27-6864e8eb17f7e3a8b444083c
m-ricΒ 
posted an update 12 days ago
view post
Post
3553
If you're using any HF libraries, you should enable the Hub MCP in your agentic coding tool!

The brand new Docs Semantic Search tool is intravenous caffeine supply for Cursor, enables to correct API errors in a few seconds, gj @mishig ⚑️⚑️

πŸ‘‰ To enable Hub MCP, head to your account setting, under MCP, and it will give you everything you need!
merveΒ 
posted an update 13 days ago
merveΒ 
posted an update 15 days ago
view post
Post
2510
so many multimodal releases these days 🀠
> ERNIE-4.5-VL: new vision language MoE models by Baidu https://huggingface.co/models?search=ernie-4.5-vl
> new visual document retrievers by NVIDIA (sota on ViDoRe!) nvidia/llama-nemoretriever-colembed-3b-v1 nvidia/llama-nemoretriever-colembed-1b-v1
> Ovis-3b: new image-text in image-text out models by Alibaba ‡️ https://huggingface.co/spaces/AIDC-AI/Ovis-U1-
thomwolfΒ 
authored a paper 18 days ago
lvwerraΒ 
authored a paper 18 days ago
merveΒ 
posted an update 19 days ago
view post
Post
592
Dataset Viewer for PDFs just landed on Hugging Face πŸ“–πŸ€— you can now preview all the PDFs easier than before!

on top of this, there's PdfFolder format to load the PDF datasets quicker πŸ’¨
> to use it, your dataset should follow a directory format like folder/train/doc1.pdf, folder/train/doc1.pdf
> if you want to include bounding boxes, labels etc. you can keep them in a metadata.csv file in the same folder 🀝

read document dataset docs https://huggingface.co/docs/datasets/main/en/document_dataset
check all the document datasets here https://huggingface.co/datasets?modality=modality:document&sort=trending πŸ“–
  • 1 reply
Β·
freddyaboultonΒ 
posted an update 20 days ago
albertvillanovaΒ 
posted an update 21 days ago
view post
Post
1583
πŸš€ SmolAgents v1.19.0 is live!
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:

πŸ”§ Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency

πŸ–₯️ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.

πŸ”„ Streaming Refactor
- Streaming event aggregation moved off the Model class
- ➑️ Better architecture & maintainability

πŸ“¦ Output Tracking
- CodeAgent outputs are now stored in ActionStep
- βœ… More visibility and structure to agent decisions

πŸ› Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching

πŸ“š Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format

πŸ”— Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0

πŸ’¬ Try it out, explore the new features, and let us know what you build!

#smolagents #opensource #AIagents #LLM #HuggingFace
merveΒ 
posted an update 21 days ago
view post
Post
639
we've merged LightGlue keypoint matcher to Hugging Face transformers! it allows commercial use when paired with an open-source keypoint detector πŸ™πŸ»

it works very well, try it yourself: ETH-CVG/LightGlue

here's an in-the-wild test with two images of the same place ‡️
  • 1 reply
Β·
merveΒ 
posted an update 21 days ago
view post
Post
4331
Release picks of the past week is here! Find more models, datasets, Spaces here merve/june-20-releases-68594824d1f4dfa61aee3433

πŸ–ΌοΈ VLMs/OCR
> moonshotai/Kimi-VL-A3B-Thinking-2506 is a powerful reasoning vision LM, 3B active params, smarter with less tokens, supports long documents, videos πŸ‘ (OS)
> nanonets/Nanonets-OCR-s is 3.75B params OCR model based on Qwen2.5VL-3B-Instruct (OS)

πŸ’¬ LLMs
> moonshotai/Kimi-Dev-72B is a strong coding model based on Qwen2.5-72B (OS)
> Mistral released mistralai/Mistral-Small-3.2-24B-Instruct-2506, an update to their former model with better function calling & instruction following (OS)

πŸ—£οΈ Audio
> Google released google/magenta-realtime, real time music generation & audio synthesis (cc-by-4)
> kyutai released new speech-to-text models that come in 1B & 2B ( kyutai/stt-1b-en_fr, stt-2b-en_fr) with 0.5s and 2.5s delay

3D
> Tencent released tencent/Hunyuan3D-2.1 an image-to-3D model (see below)
merveΒ 
posted an update 23 days ago
merveΒ 
posted an update 25 days ago
merveΒ 
posted an update 25 days ago
view post
Post
1920
stop using VLMs blindly βœ‹πŸ»

compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) πŸ”₯ visionLMsftw/comparevlms

> has support for multiple VLMs: google/gemma-3-27b-it, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen2.5-VL-32B-Instruct, meta-llama/Llama-4-Maverick-17B-128E-Instruct, HuggingFaceTB/SmolVLM2-2.2B-Instruct
> recommend us new models or inputs, we'll add 🫑

so far I figured out
> for fact-checks, you need a relatively bigger size (7B is ok!)
> Gemma 3 gets downgrade without pan and scan (especially for πŸ“‘)
> Qwen2.5VL-32B is very talkative, great for reasoning but not good for simple tasks πŸ—£οΈ
  • 2 replies
Β·